document-release
Warn
Audited by Snyk on May 15, 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 reads and acts on user-generated remote content — e.g., it calls
gh pr view --json body/glab mr viewto read andgh pr edit/glab mr updateto write PR/MR bodies, and it also consumes external artifact/brain remote URLs (via ~/.gstack-artifacts-remote.txt and gbrain remote mode); these are third-party, user-provided sources that the agent interprets and uses to decide and perform edits.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata