openspec-onboard
Warn
Audited by Snyk on Aug 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md directs the agent to read and scan the user’s local codebase for TODO/FIXME/etc. comments (e.g., “Scan the codebase… Search for
TODO,FIXME,HACK,XXXin code files”), which is outsider-authored free text that is LLM-readable at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata