codex
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly supports and demonstrates live web search (e.g., the --search flag shown in SKILL.md examples and references/cli-command-reference.md), which causes the agent/Codex to fetch and incorporate untrusted public web content into prompts and can materially influence subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata