find-bugs
Warn
Audited by Snyk on Jul 27, 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). SKILL.md instructs the agent to read a runtime
git diffoutput and then read surrounding changed file contents, which are outsider-authored free text if the branch/diff includes changes from other contributors (e.g., PR author), and that text is ingested into the LLM context as part of the review workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata