codex-review-doc

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to review documents, which introduces a risk where malicious instructions embedded in the processed data could influence the agent's behavior.
  • Ingestion points: Reads and processes document content through the Read tool and Codex MCP tools.
  • Boundary markers: None defined in this entry-point skill to isolate document content from instructions.
  • Capability inventory: The skill has access to file reading (Read, Glob), version control (Bash(git:*)), and Codex MCP interactions.
  • Sanitization: No explicit sanitization or filtering of input documents is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:38 AM
Security Audit — agent-trust-hub — codex-review-doc