codex-local-review

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is explicitly designed for read-only reviews and instructs the agent to leave the workspace unchanged.
  • [SAFE]: Analysis of the skill instructions and configuration revealed no indicators of prompt injection, data exfiltration, or malicious persistence mechanisms.
  • [SAFE]: The skill's configuration disables model-level tool invocation, which effectively limits the potential attack surface and prevents unauthorized command execution or network access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 11:48 AM
Security Audit — agent-trust-hub — codex-local-review