pr-49-review

Warn

Audited by Snyk on Feb 23, 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). SKILL.md explicitly instructs the agent to run "gh pr view 49 --json ..." and "gh pr diff 49" to fetch PR metadata and diffs from GitHub (public, user-generated content) which the agent is expected to read and use to decide review actions, so untrusted third‑party content could indirectly inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 02:19 PM