Cyera Research - Tampered copy of Anthropic's PDF skill carrying Linux Go backdoor system_linux
Cyera Research (Nov 3, 2026) discovered six skill archives impersonating Anthropic's official PDF skill, observed May 23 - July 14, 2026. Each archive contains 11 files byte-identical to upstream Anthropic…
What happened
Cyera Research (Nov 3, 2026) discovered six skill archives impersonating Anthropic's official PDF skill, observed May 23 - July 14, 2026. Each archive contains 11 files byte-identical to upstream Anthropic pdf skill (github.com/anthropics/skills), but SKILL.md is truncated from 315 lines to 19 lines keeping official name and description while replacing Quick Start section with curl https://scan.100tal.com command, and adds 5.1 MB garble-obfuscated 64-bit Linux Go ELF binary system_linux. Binary features AES-256-GCM encrypted configuration with 0xAA XOR decryption revealing C2 81.70.101.115:2345 and attaches /bin/bash over raw TCP socket. Simplified Chinese strings in binary and UTC+8 archive timestamps indicate Chinese-language development environment. scan.100tal.com hostname linked to TAL Education Group infrastructure. Cyera notes attribution is unknown and could indicate targeted attack or internal security exercise. Cyera analyzed archives but did not observe live execution of system_linux backdoor. garble obfuscator (github.com/burrowers/garble) used to strip Go function names and identifiers. Demonstrates supply-chain risk where skill typosquatting or compromised distribution channels can deliver backdoors to AI developer environments.
Supply-chain attack impersonating Anthropic's official PDF skill; tampered skill archives contain 5.1 MB garble-obfuscated Linux Go backdoor exposing developer workstations to remote shell access
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Create tampered PDF skill with system_linux backdoor
Create tampered PDF skill with system_linux backdoor
Hunt: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Source for step 1 - 02 · Truncate SKILL.md (315→19 lines), add curl scan.100tal.com
Truncate SKILL.md (315→19 lines), add curl scan.100tal.com
Hunt: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Source for step 2 - 03 · garble-obfuscate system_linux Go binary
garble-obfuscate system_linux Go binary
Hunt: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Source for step 3 - 04 · Distribute tampered skill via unknown channel
Distribute tampered skill via unknown channel
Source for step 4 - 05 · Developer installs tampered PDF skill
Developer installs tampered PDF skill
Hunt: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Source for step 5 - 06 · system_linux connects 81.70.101.115:2345, attaches /bin/bash
system_linux connects 81.70.101.115:2345, attaches /bin/bash
Hunt: A program delivered by the reported lure executes, establishes access or contacts infrastructure outside the approved software baseline.
A program name alone is not a signature. This normalized template requires the relevant platform collector and does not assert Windows-only policy coverage.
Source for step 6
Why it matters
Reported entry point: Developers install tampered PDF skill archive from unknown distribution channel (not Anthropic's official Skills repository). Reported impact: system_linux connects 81.70.101.115:2345, attaches /bin/bash; reported targets include AI developers using Claude Skills; targets include AI/ML engineering teams, research labs, and organizations deploying Anthropic skills; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Only install skills from Anthropic's official Skills repository (github.com/anthropics/skills); verify skill archive integrity and file count before installation; scan skill archives for unexpected binaries (system_linux, system_darwin, etc.); monitor skill installation for outbound connections to non-Anthropic domains (scan.100tal.com, 81.70.101.115); implement network egress filtering for skill execution environments; use read-only skill directories where possible; audit SKILL.md for truncated or modified Quick Start sections referencing external domains; educate developers on skill supply-chain risks
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Detection queries
Draft query starters grouped by the attack stages where they apply.
Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.
01Create tampered PDF skill with system_linux backdoorSkill bundle provenance / reviewCustom schema · Draft
Create tampered PDF skill with system_linux backdoor
What to look for
A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Visibility: Review / research workflow
Required logs
- Complete skill-bundle inventory and hashes
- Scanner results, extracted attachments and review history
- Agent load / tool logs if execution is actually observed
Coverage limit. Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Skill bundle provenance / review
id: 4941aba2-b392-4f04-ad39-6f0201811d26
status: experimental
description: A skill bundle introduces new network, execution or secret-access
instructions, including instructions distributed across non-Markdown files.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- skill.bundle.load
- skill.bundle.change
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("skill.bundle.load", "skill.bundle.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("skill.bundle.load", "skill.bundle.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
02Truncate SKILL.md (315→19 lines), add curl scan.100tal.comSkill bundle provenance / reviewCustom schema · Draft
Truncate SKILL.md (315→19 lines), add curl scan.100tal.com
What to look for
A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Visibility: Review / research workflow
Required logs
- Complete skill-bundle inventory and hashes
- Scanner results, extracted attachments and review history
- Agent load / tool logs if execution is actually observed
Coverage limit. Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Skill bundle provenance / review
id: 4941aba2-b392-4f04-ad39-6f0201811d26
status: experimental
description: A skill bundle introduces new network, execution or secret-access
instructions, including instructions distributed across non-Markdown files.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- skill.bundle.load
- skill.bundle.change
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("skill.bundle.load", "skill.bundle.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("skill.bundle.load", "skill.bundle.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
03garble-obfuscate system_linux Go binarySkill bundle provenance / reviewCustom schema · Draft
garble-obfuscate system_linux Go binary
What to look for
A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Visibility: Review / research workflow
Required logs
- Complete skill-bundle inventory and hashes
- Scanner results, extracted attachments and review history
- Agent load / tool logs if execution is actually observed
Coverage limit. Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Skill bundle provenance / review
id: 4941aba2-b392-4f04-ad39-6f0201811d26
status: experimental
description: A skill bundle introduces new network, execution or secret-access
instructions, including instructions distributed across non-Markdown files.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- skill.bundle.load
- skill.bundle.change
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("skill.bundle.load", "skill.bundle.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("skill.bundle.load", "skill.bundle.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
05Developer installs tampered PDF skillSkill bundle provenance / reviewCustom schema · Draft
Developer installs tampered PDF skill
What to look for
A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
Visibility: Review / research workflow
Required logs
- Complete skill-bundle inventory and hashes
- Scanner results, extracted attachments and review history
- Agent load / tool logs if execution is actually observed
Coverage limit. Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Skill bundle provenance / review
id: 4941aba2-b392-4f04-ad39-6f0201811d26
status: experimental
description: A skill bundle introduces new network, execution or secret-access
instructions, including instructions distributed across non-Markdown files.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- skill.bundle.load
- skill.bundle.change
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("skill.bundle.load", "skill.bundle.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("skill.bundle.load", "skill.bundle.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
06system_linux connects 81.70.101.115:2345, attaches /bin/bashUnexpected payload / remote-access behaviorCustom schema · Draft
system_linux connects 81.70.101.115:2345, attaches /bin/bash
What to look for
A program delivered by the reported lure executes, establishes access or contacts infrastructure outside the approved software baseline.
Apply this to system_linux execution and its connection to the reported endpoint; the IP alone is not a durable behavioral rule.
Visibility: Defender-side logs where collected
Required logs
- Platform-specific process and file provenance
- Signer / hash and software inventory
- Per-process network and remote-session records
Coverage limit. A program name alone is not a signature. This normalized template requires the relevant platform collector and does not assert Windows-only policy coverage.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Unexpected payload / remote-access behavior
id: 998d4263-6e73-4472-a74d-cb4d61c28544
status: experimental
description: A program delivered by the reported lure executes, establishes
access or contacts infrastructure outside the approved software baseline.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- process.unapproved.exec
- remote.session.start
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("process.unapproved.exec", "remote.session.start")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("process.unapproved.exec", "remote.session.start")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Confirm the payload's operating system, origin and execution context before choosing a platform-specific rule.
- Correlate the launched program with child processes, persistence and network activity; verify authorization.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- Agent / MCP as target
- Initial access
- Developers install tampered PDF skill archive from unknown distribution channel (not Anthropic's official Skills repository)
Tooling as reported
AI products, models and artifacts
- Anthropic Claude Skills (impersonated; official repo https://github.com/anthropics/skills)
- garble Go obfuscator (https://github.com/burrowers/garble)
Other tooling
- system_linux Go backdoor (5.1 MB ELF64, AES-256-GCM + 0xAA XOR config)
- /bin/bash reverse shell over TCP
Targets and reported impact
- Targets / sectors
- AI developers using Claude Skills; targets include AI/ML engineering teams, research labs, and organizations deploying Anthropic skills
- Reported scale / exposure
- Six tampered skill archives observed May 23 - July 14, 2026; Cyera analyzed archives but did not observe live system_linux execution
- Target geography
- Multiple regions
Reported attribution
Unknown actor; UTC+8 archive timestamps; Simplified Chinese strings in binary; scan.100tal.com hostname (TAL Education Group-linked); Cyera notes attribution unknown and could be targeted attack or security exercise
Structured attribution
- Actor
- Unknown
- Country
- Unknown
- Motivation
- unknown
- Attributed by
- Cyera Research
- Attribution confidence
- low
Detection rules
- Linux Shell Pipe to ShellSIGMAView rule
Detects suspicious shell pipes; relevant for detecting /bin/bash reverse shell execution from system_linux backdoor
- Bash Interactive ShellSIGMAView rule
Detects bash interactive shell spawning; directly applicable to system_linux attaching /bin/bash to TCP socket
- Skill supply-chain integrity monitoringGUIDANCE
Verify skill archives against official Anthropic Skills repository (github.com/anthropics/skills); alert on unexpected binaries in skill directories (system_linux, system_darwin); scan SKILL.md for modified Quick Start sections referencing external domains (scan.100tal.com); monitor skill installation for outbound TCP connections to non-Anthropic infrastructure (81.70.101.115:2345); detect garble-obfuscated Go binaries via string entropy analysis; flag skill archives with UTC+8 timestamps and Simplified Chinese strings when organization is not China-based
- Network egress filteringGUIDANCE
Block outbound connections from skill execution environments to unknown IPs; alert on raw TCP connections to port 2345; monitor for /bin/bash processes with network sockets; detect AES-256-GCM encrypted config files in skill directories
Activity timeline
- First seen
- 2026-05-23
- Last updated
- 2026-11-03
Updates
- 2026-05-23 — Cyera Research
Earliest observed tampered PDF skill archive with system_linux backdoor
- 2026-07-14 — Cyera Research
Latest observed tampered PDF skill archive (six total observed May 23 - Jul 14)
- 2026-11-03 — Cyera Research
Cyera publishes analysis with IOCs and backdoor mechanism; notes attribution unknown and system_linux was not observed executing
Source defensive notes
Only install skills from Anthropic's official Skills repository (github.com/anthropics/skills); verify skill archive integrity and file count before installation; scan skill archives for unexpected binaries (system_linux, system_darwin, etc.); monitor skill installation for outbound connections to non-Anthropic domains (scan.100tal.com, 81.70.101.115); implement network egress filtering for skill execution environments; use read-only skill directories where possible; audit SKILL.md for truncated or modified Quick Start sections referencing external domains; educate developers on skill supply-chain risks
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Supply-chain attack targeting AI skill distribution; tampered Anthropic PDF skill delivers Linux backdoor to developer workstations in AI/ML development environments Source
Indicators of compromise
domains
scan.100tal.com
ips
81.70.101.115
hashes
50cb53704f318e4fc9a9cd8f6d32eb98d8c666501c720d63c2c701caeb6fa946d0d4144609825ee7480f7889ee04d97f4b1d9eaa8a46c2a0d46d81ab5aa83827
urls
https://scan.100tal.com (TAL Education Group-linked hostname)
Sources & research credit
1 sourceResearch by Assaf Morag · Cyera Research
Cyera Research (Assaf Morag, Nov 3, 2026) primary source; all hashes from Cyera IoC table: system_linux SHA-256 50cb53704f318e4fc9a9cd8f6d32eb98d8c666501c720d63c2c701caeb6fa946, SKILL.md SHA-256 d0d4144609825ee7480f7889ee04d97f4b1d9eaa8a46c2a0d46d81ab5aa83827, plus archive hashes; network IOCs 81.70.101.115 and scan.100tal.com verified from Cyera; Cyera explicitly states archives were analyzed but system_linux was not observed executing
Record & downloads
- Source record name
- Cyera Research - Tampered copy of Anthropic's PDF skill carrying Linux Go backdoor system_linux
- Entry ID
- cyera-anthropic-pdf-skill-backdoor-2026-11
- Catalog review
- November 6, 2026
- Category
- attacks-on-ai
- AI involvement confidence
- confirmed