codex-claude-loop
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow’s runtime sends a user-authored task plan and implementation text into
codex execviaecho "...[Claude's plan here]..." | codex exec ...andecho "Review this implementation..." | codex exec ..., so outsider free text flows into the validator without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata