retro
Warn
Audited by Snyk on Jul 15, 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). SKILL.md’s required workflow reads local repository history and files authored by other contributors (e.g.,
git log ... --format=...andgit log ... --format="AUTHOR:%aN" --name-only, plus optionalcat ~/.gstack/greptile-history.mdandcat TODOS.md), which becomes free-text input to the agent’s LLM for narrative generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata