gitnexus-pr-review
Warn
Audited by Snyk on Mar 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches PR diffs via "gh pr diff" (GitHub pull request content) and reads repository artifacts (gitnexus://repo/...), which are user-generated third-party inputs the agent ingests and uses to drive analysis and merge/review decisions, creating potential for indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime "READ gitnexus://repo/{name}/processes" operation that fetches repository process data into the agent's context (gitnexus://repo/{name}/processes), which directly controls the agent's analysis/prompting and is a required dependency for reviews.
Audit Metadata