update-mr-desc
Warn
Audited by Snyk on Feb 28, 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 explicitly instructs the agent to fetch and summarize Merge Request diffs from GitLab (via MCP or the glab CLI) — which are user-generated/untrusted MR contents that the agent must read and interpret to produce/update the MR description — creating a clear avenue for indirect prompt injection via crafted diffs.
Audit Metadata