issue-create
Warn
Audited by Snyk on Mar 6, 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 fetches repository data from GitHub (e.g., "gh label list --repo OWNER/REPO" and related-issues searches described in SKILL.md and references/label-strategy.md/ai-prompts.md), and it feeds repository labels and issue content (user-generated, potentially public) into AI prompts to pick labels and detect/link similar issues, so third-party content can materially influence decisions.
Audit Metadata