# GPUStack CVE-2026-102895 loopback admin bypass used to plant reverse-shell inference backends

- ID: gpustack-cve-2026-102895-reverse-shell-2026-11
- Reported: 2026-11-09
- Researcher: Nikko Enggaliano; Wei Yunzhou; Rui Yang and Haoyu Wang (Johns Hopkins University); in-the-wild case reported by Javier Sixto (ulex.fr); advisory by gitlawr
- Organization: GPUStack
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-12
- Entry page: https://openattacks.ai/attacks/gpustack-cve-2026-102895-reverse-shell-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/gpustack-cve-2026-102895-reverse-shell-2026-11.json
- Browse title: GPUStack CVE-2026-102895 loopback admin bypass used to plant reverse-shell inference backends
- Editorial summary: GPUStack before v2.2.0 treats a request as the built-in administrator when get\_current\_user in gpustack/api/auth.py decides the source is loopback and force\_auth\_localhost is false, which is the default. A…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/gpustack-cve-2026-102895-reverse-shell-2026-11.json

## Technique
GPUStack before v2.2.0 treats a request as the built-in administrator when get\_current\_user in gpustack/api/auth.py decides the source is loopback and force\_auth\_localhost is false, which is the default. A remote attacker can look like loopback in two ways. Behind a same-host reverse proxy that uses proxy\_pass to 127.0.0.1, every request arrives with TCP peer 127.0.0.1. A forged X-GPUStack-Real-IP: 127.0.0.1 header can also make client\_ip\_getter report loopback. Either path yields full admin with no credentials. The attacker can enumerate and change users, models, workers, and configuration, mint persistent admin API keys with scope \["\*" \] that stay valid from any IP afterward, and read worker credentials and cloud or provider secrets. POST /v2/inference-backends/from-yaml runs code on worker hosts. The vendor advisory, published by gitlawr, says this was exploited in the wild against a v2.1.1 deployment, where attackers created custom inference backends that ran reverse shells. Keys minted before the patch keep working after the upgrade. Affected package is gpustack on pip below 2.2.0. Fixed in 2.2.0. Workaround is force\_auth\_localhost=true. CISA added CVE-2026-102895 / GHSA-gj9m-f8ph-pmhr to the Known Exploited Vulnerabilities catalog on Nov 9, 2026, with a due date of Nov 12 and a note to apply forensic triage. The vulnerability was reported independently by Nikko Enggaliano, Wei Yunzhou, and Rui Yang and Haoyu Wang of Johns Hopkins University. Javier Sixto of ulex.fr reported the in-the-wild case. No attacker IPs or hashes were published. Project: https://github.com/gpustack/gpustack.

## 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
Unauthenticated admin via loopback trust: same-host reverse proxy or forged X-GPUStack-Real-IP header

## AI tooling and models
- GPUStack inference platform (https://github.com/gpustack/gpustack), versions before 2.2.0, exploited on 2.1.1

## Other tooling
- Custom inference backends created through POST /v2/inference-backends/from-yaml
- Admin API keys with scope \["\*"\]

## Victims and sectors
Organizations serving models with GPUStack; one confirmed v2.1.1 deployment

## Target geography
- unknown

## Attribution
Unnamed. CISA confirmed exploitation by adding the CVE to KEV. The GPUStack advisory documents the in-the-wild reverse-shell case. No country or motivation is stated.

## Scale and metrics
CISA KEV dateAdded 2026-11-09, due 2026-11-12. One described in-the-wild deployment on v2.1.1. No victim count published.

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### bypass: Appear as loopback [access]
A remote request arrives through a same-host reverse proxy or sends X-GPUStack-Real-IP: 127.0.0.1, and GPUStack logs it in as the built-in admin.
Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr

### mint-key: Mint an admin API key [execution]
The attacker creates an API key with scope star that remains valid from any source IP after the patch.
Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr

### backend: Register a malicious inference backend [ai]
POST /v2/inference-backends/from-yaml installs a custom backend on worker hosts.
Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr

### shell: Reverse shell on the worker [impact]
In the observed v2.1.1 case, the custom backend ran a reverse shell.
Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr

Connections:
- bypass -> mint-key
- mint-key -> backend
- backend -> shell

## 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.
### bypass: Web exploitation → host activity
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/web.sigma.yml
- KQL query download: /api/detections/web.kql
- SPL query download: /api/detections/web.spl
- Hunt hypothesis: Repeated exploit or upload requests are followed by an unexpected server process, file, or outbound connection.
- Required telemetry: Reverse-proxy / WAF request logs; Server process and file events; Outbound DNS / proxy records
- Investigate: Join requests to the affected host and process tree by time and request ID.
- Investigate: Inspect uploaded files and server-spawned shells; distinguish authorized testing from exploitation.
- Limitation: A scan or high request rate alone does not prove compromise or AI use. Host telemetry is needed to confirm execution.
- No direct MagicSword prevention claim is recorded for this stage.

### mint-key: Sensitive store access → credential use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/credentials.sigma.yml
- KQL query download: /api/detections/credentials.kql
- SPL query download: /api/detections/credentials.spl
- Hunt hypothesis: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
- Required telemetry: File-read / API access telemetry for relevant secret stores; Process identity and command lines; Identity, token and outbound-network audit logs
- Investigate: Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Investigate: Correlate reads with egress and rotate affected credentials after confirming exposure.
- Limitation: Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
- No direct MagicSword prevention claim is recorded for this stage.

### backend: 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.

### shell: Linux fileless or anonymous-file execution
- Visibility: Linux process and audit telemetry where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/linux-fileless-execution.sigma.yml
- KQL query download: /api/detections/linux-fileless-execution.kql
- SPL query download: /api/detections/linux-fileless-execution.spl
- Hunt hypothesis: A Linux process executes from a memfd or /proc file-descriptor path, or stages an executable in a transient directory, consistent with fileless payload or miner execution.
- Required telemetry: Linux process creation with executable paths and command lines; Audit or EDR telemetry for memfd\_create and execve where available; Network and persistence activity from the resulting process
- Investigate: Capture the process memory or recovered executable, parent tree, user, container, and destination.
- Investigate: Correlate the execution with downloads, persistence changes, mining traffic, or reverse shells.
- Limitation: Updaters, runtimes, and security tools can legitimately execute anonymous files. Process collectors differ in how they represent memfd paths, so absence of a match is not proof of absence.
- 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.T0049: Exploit Public-Facing Application — The loopback-trust bug is a public-facing authentication bypass in the GPUStack API
  Technique: https://atlas.mitre.org/techniques/AML.T0049
  Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr
- AML.T0012: Valid Accounts — Attackers mint persistent admin API keys with scope star that survive the patch
  Technique: https://atlas.mitre.org/techniques/AML.T0012
  Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr
- AML.T0050: Command and Scripting Interpreter — POST /v2/inference-backends/from-yaml runs attacker commands on worker hosts
  Technique: https://atlas.mitre.org/techniques/AML.T0050
  Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr
- AML.T0072: Reverse Shell — The in-the-wild case used custom inference backends that ran reverse shells
  Technique: https://atlas.mitre.org/techniques/AML.T0072
  Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr
- AML.T0055: Unsecured Credentials — Admin access exposes worker credentials and cloud or provider secrets
  Technique: https://atlas.mitre.org/techniques/AML.T0055
  Evidence: https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr

## Defensive notes
Upgrade gpustack to 2.2.0 or later. Set force\_auth\_localhost=true until upgraded. Strip client-supplied X-GPUStack-Real-IP at the edge. Do not front GPUStack with a same-host reverse proxy that makes every request look like 127.0.0.1. Revoke admin API keys minted before the patch, including keys with scope \["\*"\]. Hunt worker hosts for reverse shells started by custom inference backends.

## Sources
- https://github.com/gpustack/gpustack/security/advisories/GHSA-gj9m-f8ph-pmhr — GHSA-gj9m-f8ph-pmhr: GPUStack authentication bypass via trusted loopback source
- https://www.cisa.gov/known-exploited-vulnerabilities-catalog — CISA Known Exploited Vulnerabilities Catalog (CVE-2026-102895 added 2026-11-09)
- https://nvd.nist.gov/vuln/detail/CVE-2026-102895 — NVD: CVE-2026-102895
- https://thehackernews.com/2026/11/cisa-warns-of-active-exploitation-of.html — The Hacker News: CISA warns of active exploitation of GPUStack

## Source notes
Behavior, header, endpoint, version, and the in-the-wild reverse-shell statement are from GHSA-gj9m-f8ph-pmhr. CISA KEV and NVD pages returned HTTP 403 to this reviewer's fetch but are the canonical catalog and CVE records cited by the advisory coverage. No IPs or hashes were published, so none are listed.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
