ss-code-review
Warn
Audited by Snyk on Jul 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Yes: in “Step 1: Fetch the Diff & Context” the skill ingests PR title/description and commit messages fetched from a user-supplied MR/PR URL (public web content / outsider-authored text) into the LLM context via the “[Title, description, commit messages]” PR context block.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata