CVE-2026-54785: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in eLyiN gemini-bridge
gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI. From 1.0.0 until 1.3.1, consult_gemini_with_files in inline mode read any file path supplied in the files argument without confining it to the working directory, then forwarded the contents to the Gemini CLI. Because the caller also controls query, the file contents are echoed back through the Gemini round-trip (and sent to Google), making this an arbitrary local file read. This issue is fixed in version 1.3.1.
AI Analysis
Technical Summary
The gemini-bridge software, versions 1.0.0 up to but not including 1.3.1, contains a path traversal vulnerability (CWE-22) in the consult_gemini_with_files function when used in inline mode. This function reads any file path provided in the files argument without restricting access to the working directory. Because the query parameter is also controlled by the caller, the contents of the arbitrarily read files are echoed back through the Gemini AI round-trip and sent to Google, resulting in an arbitrary local file read vulnerability (CWE-200). The vulnerability is resolved in version 1.3.1.
Potential Impact
An attacker with local access or the ability to invoke the vulnerable function can read arbitrary files on the system running gemini-bridge. This can lead to unauthorized disclosure of sensitive information. The vulnerability does not allow code execution or denial of service. The CVSS v3.1 base score is 6.2 (medium severity), reflecting the local attack vector and high confidentiality impact.
Mitigation Recommendations
Upgrade gemini-bridge to version 1.3.1 or later, where this vulnerability is fixed. No other official remediation or temporary workaround is documented. Patch status is not explicitly stated but the fix is included in version 1.3.1.
CVE-2026-54785: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in eLyiN gemini-bridge
Description
gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI. From 1.0.0 until 1.3.1, consult_gemini_with_files in inline mode read any file path supplied in the files argument without confining it to the working directory, then forwarded the contents to the Gemini CLI. Because the caller also controls query, the file contents are echoed back through the Gemini round-trip (and sent to Google), making this an arbitrary local file read. This issue is fixed in version 1.3.1.
CVSS v3.1
Score 6.2medium
Affected software
eLyiN
gemini-bridge
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The gemini-bridge software, versions 1.0.0 up to but not including 1.3.1, contains a path traversal vulnerability (CWE-22) in the consult_gemini_with_files function when used in inline mode. This function reads any file path provided in the files argument without restricting access to the working directory. Because the query parameter is also controlled by the caller, the contents of the arbitrarily read files are echoed back through the Gemini AI round-trip and sent to Google, resulting in an arbitrary local file read vulnerability (CWE-200). The vulnerability is resolved in version 1.3.1.
Potential Impact
An attacker with local access or the ability to invoke the vulnerable function can read arbitrary files on the system running gemini-bridge. This can lead to unauthorized disclosure of sensitive information. The vulnerability does not allow code execution or denial of service. The CVSS v3.1 base score is 6.2 (medium severity), reflecting the local attack vector and high confidentiality impact.
Mitigation Recommendations
Upgrade gemini-bridge to version 1.3.1 or later, where this vulnerability is fixed. No other official remediation or temporary workaround is documented. Patch status is not explicitly stated but the fix is included in version 1.3.1.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-06-15T23:23:57.714Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a6d263fbf32cb7a3478a194
Added to database: 07/31/2026, 22:48:31 UTC
Last enriched: 08/08/2026, 14:30:25 UTC
Last updated: 09/14/2026, 22:01:35 UTC
Views: 73
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.