gitlab-api
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and parse user-generated merge request discussions and note bodies from GitLab endpoints (e.g., calls to https://gitlab.example.com/api/graphql and REST issue endpoints in "Workflow 1" and "Workflow 2"), which are untrusted third-party content that the agent reads and uses to decide actions like creating or linking issues.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata