skills/mrshu/agent-skills/codex-exec/Gen Agent Trust Hub

codex-exec

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the codex CLI tool using various flags (e.g., --base, --uncommitted, --commit) and commands (review, exec). This allows for automated analysis of the local codebase and version control history.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it ingests and processes content from the local codebase, git diffs, and specific files like PLAN.md through the codex tool.
  • Ingestion points: Source code files and git history diffs processed via codex review and codex exec in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential adversarial commands embedded within the code or files being reviewed.
  • Capability inventory: The skill uses the codex command-line utility for processing data.
  • Sanitization: There is no mention of sanitization or filtering of the content being reviewed or the output generated by the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 05:36 PM
Security Audit — agent-trust-hub — codex-exec