review-fix-codex

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @willbooster/agent-skills package from the npm registry using the bunx command.
  • [COMMAND_EXECUTION]: Executes shell commands to run code reviews and performs git operations, including committing and pushing changes to the repository.
  • [PROMPT_INJECTION]: Contains a surface for indirect prompt injection where the agent is instructed to follow suggestions provided by an external tool's output.
  • Ingestion points: review results returned by bunx @willbooster/agent-skills@latest review --agent codex in SKILL.md.
  • Boundary markers: None provided to distinguish review comments from system instructions.
  • Capability inventory: Ability to modify local source code and push changes to a remote repository.
  • Sanitization: No validation or sanitization of the review comments before they are used to influence code changes.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 09:33 PM
Security Audit — agent-trust-hub — review-fix-codex