skills/shhac/agent-skills/agent-code-review/Snyk

agent-code-review

Warn

Audited by Snyk on Jul 10, 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). The required workflow (“agent-code-review run/serve” reviewing PRs) necessarily fetches live PR metadata/content from GitHub for candidate PRs, so outsider-authored free text from PR bodies/comments/discussion is ingested into the LLM prompt via the review engine’s assembled prompt.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 10, 2026, 11:24 AM

Issues

1

Security Audit — snyk — agent-code-review