feature-branch
Warn
Audited by Snyk on Mar 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md Step 1 explicitly instructs fetching a GitHub issue with
gh issue view(a user-generated, potentially public third‑party source) and then uses that issue text to generate branch names and summaries, so external content is ingested and can influence agent actions.
Audit Metadata