codex-review
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md instructs running
codex reviewand then reading Codex’s generatedreport.mdback into the agent (“Read Codex's report…”), so the LLM ingests outsider-authored free text produced by the externalcodexCLI at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata