codex

Warn

Audited by Snyk on May 20, 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 explicitly calls the external Codex CLI with web search enabled (see multiple places: Review/Challenge/Consult steps use codex with --enable web_search_cached), so it will fetch and ingest public web content and use that output verbatim to decide gate PASS/FAIL and produce recommendations—allowing untrusted third‑party content to materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 05:21 PM
Issues
1
Security Audit — snyk — codex