gitlab-automation
Warn
Audited by Snyk on Oct 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill automates reading GitLab issues, merge requests, commits, and project content via MCP tools, which ingest outsider-authored free text from repositories and tickets.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill references an external MCP server endpoint (
https://rube.app/mcp) in its setup instructions to be added as an MCP server, presenting an unverifiable external runtime dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata