grill-me
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads the user's supplied proposal, repository code, tests, and docs, plus "declared sources" that the agent may look up itself (SKILL.md:13), so outsider-authored web content is reachable only if the agent actively fetches it, which is a low-risk path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata