gitlab-discussion
Warn
Audited by Snyk on Feb 20, 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). SKILL.md explicitly instructs using glab api to fetch GitLab discussions (e.g., "List MR discussions" and "Workflow 2: Resolve All Discussions" which call glab api projects/:id/.../discussions), thereby ingesting user-generated discussion bodies that the workflows read and act on (list, summarize, resolve), so third-party content can influence agent actions.
Audit Metadata