skill-judge
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill’s runtime LLM context is populated from the user-provided SKILL.md text to be evaluated (a free-form document authored by an outsider to the operating user), which the agent then reads and includes in its analysis context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata