Servers and applications
GHSA-wfhw-9fr5-x7xg
Duplicate tool-call IDs can alias tool-approval decisions
- Severity
- High 8.8
- Published
- 17 Nov 2026
- Last changed
- 17 Nov 2026
- Added to UpHeron
- 17 Nov 2026
- Attack
- Over the network · No login needed · Needs someone to click or open something
- Attacker can
- Read data · Change data · Take it down
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H- Sources
- Project advisories (GitHub)
Description
LibreChat accepts two approval-gated MCP tool calls with different arguments but the same provider-supplied tool_call.id. It displays one approval card for the benign call, but approving it authorizes and executes both calls. This allows a hidden MCP operation to run without being independently displayed or approved by the user.
LibreChat uses tool_call.id as the authorization identity across presentation, approval, and execution, but does not reject duplicate IDs within one pending approval batch.
The provider can return:
Both calls are retained, but the UI exposes one effective approval card showing benign-blue. When the user approves that card, the submitted decision for shared-call-id is applied to both occurrences and both MCP calls execute.
The vulnerable flow is present in:
- packages/api/src/agents/hitl/policy.ts: buildToolApprovalPayload() preserves duplicate IDs without validation.
Affected software
| Software | Affected versions |
|---|---|
LibreChatServers and applications · github:librechat-ai/librechat |
|
About LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
- Docker Hub pulls
- 669,094Docker Hub, 15 Nov 2026
- GitHub stars
- 47,138GitHub, 15 Nov 2026
- Forks
- 9,706GitHub, 15 Nov 2026
- License
- MITGitHub
- First published on GitHub
- 12 Feb 2023GitHub
Source code Website Docker image
Vulnerabilities in LibreChat
- In our list
- 104
- Published in the last 12 months
- 84
- Critical, last 12 months
- 5
- High, last 12 months
- 25
- Known exploited
- 0
- CVE-2026-54041Plaintext password logged on login validation errorLow 3.1 17 Nov 2026
- CVE-2026-54032Remote MCP Server Description XSS via Unsanitized dangerouslySetInnerHTML; secondary Admin Banner sink lacks DOMPurifyMedium 6.1 17 Nov 2026
- CVE-2026-54026Cross-User Message Injection via Parameter Confusion in LibreChatMedium 6.5 17 Nov 2026
- CVE-2026-54031MCP OAuth requests can follow redirects to internal URLs after SSRF validationMedium 6.3 17 Nov 2026
- CVE-2026-54038Server-Side ReDoS via Unescaped Regex in Principal SearchMedium 6.5 17 Nov 2026
- CVE-2026-54045Password Reset Can Wipe Email-Verification Tokens When Verification Is EnforcedMedium 6.5 17 Nov 2026
References
- GitHub Advisory Database https://github.com/advisories/GHSA-wfhw-9fr5-x7xg
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-wfhw-9fr5-x7xg