Quality Tools

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents standard, local command-line tools for static code analysis, formatting, and type checking across multiple languages (JS/TS, Go, Rust, Nix, Python, etc.).\n- [SAFE]: No network operations, remote script downloads, or credential-accessing patterns were identified.\n- [SAFE]: The refactoring operations and scored review patterns provide benign architectural guidance and follow standard development practices.\n- [PROMPT_INJECTION]: The skill defines tools that process external source code files. While code could theoretically contain malicious instructions targeting the agent, the defined tools are standard industry linters and formatters used for their intended purpose.\n
  • Ingestion points: Source code files passed to commands as arguments in SKILL.md (e.g., [files], ./...).\n
  • Boundary markers: None present in the tool definitions.\n
  • Capability inventory: Execution of local CLI tools such as eslint, ruff, tsc, and cargo via the agent's command execution capabilities.\n
  • Sanitization: None; tools are expected to parse and analyze the raw file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 05:21 AM
Security Audit — agent-trust-hub — Quality Tools