to-spec
Warn
Audited by Snyk on Aug 21, 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). In
SKILL.md, the skill’s runtime path explicitly takes “the current conversation context” and then synthesizes and publishes a spec to the project issue tracker, meaning outsider-authored free text from the conversation can be ingested and used without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata