gitlab-automation
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly requires calling GitLab APIs (e.g., GITLAB_LIST_PROJECT_ISSUES, GITLAB_GET_PROJECT_MERGE_REQUESTS, GITLAB_GET_USERS) to fetch issues, merge requests, comments and user data from a third-party GitLab instance, and those user-generated contents are read and used to drive decisions and follow-up tool actions described in the Core Workflows.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill requires connecting to the Rube MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch current tool schemas that directly determine agent behavior, making this a required external runtime dependency.
Audit Metadata