grill-product
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow explicitly gathers “outside voices” via web search and
gh(e.g., reviews, forums, competitor pages, and GitHub issues/discussions), which are outsider-authored free text that can be ingested into the agent’s LLM context through the subagents’ returned digests/quotes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata