github-workflow
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflows (e.g., the "Self-Healing Pipeline" and "Failure Analysis" examples in SKILL.md) call GitHub CLI commands like "gh run view ... --log" and "gh run view $RUN_ID --log-failed" and parse run logs/issue bodies to decide fixes and create issues, meaning it ingests untrusted, user-generated GitHub repository logs and content and uses them to drive automated decisions and actions.
Audit Metadata