codex-code-review

Warn

Audited by Snyk on May 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 reads user-generated PR metadata via gh pr view (title/description), fetches diffs (git diff -> /tmp/codex-diff-...), and reads the full source of changed files (from the repo/PR) and then feeds that content into Codex prompts and decision-making, so untrusted third-party PR/web-hosted content can materially influence tool actions and behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 07:04 AM
Issues
1
Security Audit — snyk — codex-code-review