planning
Warn
Audited by Snyk on Feb 24, 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). SKILL.md explicitly instructs the agent to read GitHub Issues (via "gh sub-issue list ") and ingest issue titles, labels, and bodies—user-generated, untrusted third-party content—which is then used to determine dependencies and drive planning decisions.
Audit Metadata