adversarial-spec
Warn
Audited by Snyk on Feb 26, 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 supports web searching via the Codex CLI (see SKILL.md "Codex CLI Setup" with "Web search: --codex-search") and scripts/models.py's call_codex_model passes --search to the Codex CLI and feeds the returned public web content into model prompts and critiques, so untrusted third‑party webpages can be ingested and influence the agent's decisions.
Audit Metadata