writing-skills
Warn
Audited by Snyk on Aug 26, 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
testing-skills-with-subagents.mdthe runtime workflow explicitly has the agent run pressure scenarios and “document choices and rationalizations verbatim,” which uses outsider-authored scenario text supplied in the task prompt (e.g., the human’s “IMPORTANT: This is a real scenario. Choose and act.” blocks) without first selecting any trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata