# Radware hidden prompt injection targeting GitHub maintainer bots

- ID: radware-github-prompt-injection-bots-2026-11
- Reported: 2026-11-05
- Researcher: Zvika Babo, Gabi Nakibly
- Organization: Radware
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-10
- Entry page: https://openattacks.ai/attacks/radware-github-prompt-injection-bots-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/radware-github-prompt-injection-bots-2026-11.json
- Browse title: Radware hidden prompt injection targeting GitHub maintainer bots
- Editorial summary: Radware researchers Zvika Babo and Gabi Nakibly (Nov 5, 2026) document hidden prompt injection techniques targeting GitHub maintainer bots processing issues and pull requests. Attackers hide instructions in…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/radware-github-prompt-injection-bots-2026-11.json

## Technique
Radware researchers Zvika Babo and Gabi Nakibly (Nov 5, 2026) document hidden prompt injection techniques targeting GitHub maintainer bots processing issues and pull requests. Attackers hide instructions in HTML comments, invisible Unicode characters, and CSS display tricks. Examples documented: (1) google-gemini/gemini-cli\#28575 - deduplication agent told to use run\_shell\_command to write base64-encoded GITHUB\_TOKEN into GITHUB\_ENV; (2) openai/codex\#16733 - labeler told to curl webhook.site and dump environment variables; (3) microsoft/agent-framework\#7177 - fake triage gate with allow\_triage=true, gate\_result=pass markers; (4) blondesean/Kings\_Herald\#21 - hidden backdoor instruction in feature request. Attackers study bot tool names and output field formats to forge steering markers. Hidden instructions can bypass human review while manipulating bot behavior. Radware provides examples repository at github.com/rdwr-gabin/github-ipi-in-the-wild. No specific threat actor attribution; confirmed technique active in wild.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Malicious GitHub issues or pull requests with hidden prompt injection

## AI tooling and models
- GitHub triage bots
- GitHub review bots
- GitHub CI/CD automation bots
- Repository automation agents

## Other tooling
- HTML comments
- Invisible Unicode characters
- CSS display manipulation
- [webhook.site](https://github.com/webhooksite/webhook.site) exfiltration

## Victims and sectors
GitHub repositories using AI-powered triage, review, and CI bots; examples include Google Gemini, OpenAI, Microsoft repositories

## Target geography
- Multiple regions

## Attribution
Unattributed technique; confirmed active in wild with documented examples

## Scale and metrics
Multiple confirmed examples across major repositories (Google, OpenAI, Microsoft); active Nov 2026

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### study-bots: Study bot tools and output formats [execution]
Attacker analyzes target repository bot behavior, tool names, and expected output field formats
Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

### craft-injection: Craft hidden prompt injection [execution]
Embed instructions in HTML comments, invisible Unicode, or CSS-hidden elements
Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

### submit-issue-pr: Submit malicious issue or PR [access]
Attacker creates GitHub issue or PR containing hidden instructions
Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

### bot-processes: Bot processes issue/PR [ai]
Triage, review, or CI bot reads issue/PR including hidden injection
Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

### execute-injection: Bot executes injected instructions [impact]
Bot writes GITHUB\_TOKEN to env, curls webhook, or accepts fake triage gate
Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

Connections:
- study-bots -> craft-injection
- craft-injection -> submit-issue-pr
- submit-issue-pr -> bot-processes
- bot-processes -> execute-injection

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### study-bots: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### craft-injection: Untrusted content enters an agent session
- Visibility: Application / agent audit records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-input.sigma.yml
- KQL query download: /api/detections/agent-input.kql
- SPL query download: /api/detections/agent-input.spl
- Hunt hypothesis: An agent ingests external content or an untrusted session identifier before a tool action or configuration change outside the approved task.
- Required telemetry: Input provenance, source type and request/session identifier; Captured tool responses or retrieved content where collection is approved; Subsequent tool calls, configuration changes and approval decisions
- Investigate: Join the ingested input to later actions by session or request ID; preserve the original content as evidence.
- Investigate: Compare the resulting action with the approved task and baseline. Receiving suspicious text alone is not successful injection.
- Limitation: Requires application instrumentation and a custom field mapping. Input exposure does not prove that the model followed instructions, executed a tool or bypassed approval. Avoid collecting sensitive prompt bodies unless authorized.
- No direct MagicSword prevention claim is recorded for this stage.

### submit-issue-pr: Private access → public repository artifact
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/repository.sigma.yml
- KQL query download: /api/detections/repository.kql
- SPL query download: /api/detections/repository.spl
- Hunt hypothesis: A token or agent reads private material and creates a public issue, repository, commit or visibility change inconsistent with the approved task.
- Required telemetry: Git-provider organization / enterprise audit; Repository and token permission inventory; Agent tool and secret-scanning / DLP records
- Investigate: Join access and public-write actions by actor / token and time; inspect visibility changes and newly created repositories.
- Investigate: Verify whether the artifact contains sensitive data using approved scanning, retaining original source qualifications.
- Limitation: Git-provider audit completeness depends on product and plan. Not every file read or issue body is present in organization audit logs.
- No direct MagicSword prevention claim is recorded for this stage.

### bot-processes: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### execute-injection: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0051: LLM Prompt Injection — Hidden HTML comments, invisible Unicode, and CSS tricks inject instructions into GitHub bot processing
  Technique: https://atlas.mitre.org/techniques/AML.T0051
  Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/
- AML.T0053: AI Agent Tool Invocation — Bots manipulated to execute run\_shell\_command, curl webhooks, write GITHUB\_TOKEN to environment
  Technique: https://atlas.mitre.org/techniques/AML.T0053
  Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/
- AML.T0055: Unsecured Credentials — Attackers study bot tool names/output fields to forge valid steering markers (allow\_triage, gate\_result)
  Technique: https://atlas.mitre.org/techniques/AML.T0055
  Evidence: https://www.radware.com/blog/prompt-injecting-coding-agents/

## Defensive notes
Strip HTML comments before bot processing; sanitize invisible Unicode from issues/PRs; validate bot tool output fields against expected schema; implement bot action approval gates; monitor for suspicious run\_shell\_command, curl webhook, environment variable access; restrict bot permissions to minimum required; log all bot actions for audit; educate maintainers on prompt injection risks; implement bot behavioral analysis

## Sources
- https://www.radware.com/blog/prompt-injecting-coding-agents/ — Radware: Prompt Injecting Coding Agents
- https://github.com/rdwr-gabin/github-ipi-in-the-wild — Radware: GitHub IPI in the Wild - Examples Repository

## Source notes
Radware blog (Nov 5, 2026) primary source; examples repository github.com/rdwr-gabin/github-ipi-in-the-wild provides proof-of-concept demonstrations; links to hackerbot-claw-github-actions-2026-03 and forever-agents-md-hijack catalog entries for related GitHub AI agent attacks

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [
    "webhook.site"
  ],
  "ips": [],
  "hashes": [],
  "urls": [
    "https://github.com/google-gemini/gemini-cli/issues/28575",
    "https://github.com/openai/codex/issues/16733",
    "https://github.com/microsoft/agent-framework/issues/7177",
    "https://github.com/blondesean/Kings_Herald/issues/21",
    "https://github.com/rdwr-gabin/github-ipi-in-the-wild"
  ]
}
```
