project-standards-reviewer

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it is designed to discover and follow instructions found within repository standards files.
  • Ingestion points: The agent uses the Read and Glob tools to retrieve content from CLAUDE.md, AGENTS.md, and other project files (SKILL.md).
  • Boundary markers: No delimiters or protective instructions are used to separate the contents of these files from the agent's internal logic (SKILL.md).
  • Capability inventory: The skill utilizes the Bash, Read, Grep, and Glob tools, providing a wide interaction surface (SKILL.md).
  • Sanitization: No validation or sanitization is performed on the content extracted from the repository files (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:31 AM