meta-reviewing-cli-reviewing

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze external CLI code, which serves as an ingestion point for potential indirect prompt injection. 1. Ingestion points: User-provided CLI source code and pull request data. 2. Boundary markers: The skill does not define specific delimiters to isolate the code being reviewed from the agent's instructions. 3. Capability inventory: The agent typically has capabilities for file system interaction and command execution within its environment. 4. Sanitization: No explicit instructions are provided for sanitizing or escaping the input code before analysis.
  • [EXTERNAL_DOWNLOADS]: Fetches a metadata validation schema from the author's official GitHub repository to ensure metadata integrity.
  • [NO_CODE]: No executable scripts, binaries, or active code components are shipped with this skill; it consists entirely of instructional documentation.
  • [SAFE]: The skill provides constructive security guidance, specifically advising reviewers to check for shell injection vulnerabilities and improper secrets handling in the reviewed code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:32 AM