codex-code-review
Warn
Audited by Snyk on Apr 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.80). This skill explicitly instructs running the Codex CLI with the --dangerously-bypass-approvals-and-sandbox flag (i.e., bypassing the bwrap sandbox and weakening security) and tells the agent to access the filesystem and run commands, which is a direct instruction to bypass security mechanisms even if described as "read-only."
Issues (1)
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata