explain-diff
Warn
Audited by Snyk on Jul 20, 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 workflow can fetch and read outsider-authored PR diff/content at runtime (public web/PR pages or their text via the “
--pr <n|url>” path), and then turns that diff/hunks into LLM-visible prose/HTML evidence, creating an indirect prompt-injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata