claude-code-usage
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists of documentation and behavioral guidelines for a coding assistant. It contains no executable code, network operations, or obfuscated content.
- [DATA_EXFILTRATION] (SAFE): The skill actively promotes security best practices by instructing the agent and user to avoid 'git add .' to prevent the accidental commitment of sensitive '.env' files.
- [COMMAND_EXECUTION] (SAFE): References to 'forge' (Foundry) and 'git' commands are appropriate for the skill's stated purpose of supporting Solidity development. There are no patterns suggesting the execution of untrusted or remote scripts.
- [PROMPT_INJECTION] (LOW): The use of '[AUTO-INVOKE]' and imperative language like 'MUST be invoked' are meta-instructions for workflow management. They do not attempt to bypass core AI safety guardrails or extract system prompts.
Audit Metadata