skills/tingyulu/myr2d2/ai-review/Gen Agent Trust Hub

ai-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The ai-review.sh script and the SKILL.md documentation include a help message suggesting the user install the Codex CLI using curl -fsSL https://chatgpt.com/codex/install.sh | sh. This URL belongs to a well-known service (OpenAI), and the script provides the command as information for the user rather than executing it automatically.
  • [DYNAMIC_EXECUTION]: The script implements a pluggable backend architecture via the AI_REVIEW_CMD environment variable. When set, the script executes the provided command string using sh -c. This is an intended feature for extensibility, allowing users to swap the default Codex CLI for other local or remote models.
  • [INDIRECT_PROMPT_INJECTION]: The skill takes file content or stdin as input and interpolates it into a prompt for a third-party LLM. This creates a surface for indirect prompt injection. To mitigate this, the script uses explicit boundary markers (=== 原文 ===) and includes clear system instructions for the reviewer model to treat the content as data only and avoid executing any instructions contained within it.
  • [COMMAND_EXECUTION]: The skill uses standard POSIX shell utilities (mktemp, sed, cat, printf, date) for file handling and prompt assembly. It follows security best practices by using mktemp for temporary files, trap for cleanup, and chmod 600 to restrict access to saved review results.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:39 PM
Security Audit — agent-trust-hub — ai-review