code-formatter
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill does not contain any instructions that attempt to bypass AI safety guidelines, override system prompts, or assume unrestricted roles.
- [DATA_EXFILTRATION] (SAFE): No patterns of sensitive file access or unauthorized network requests were found. Code examples containing placeholders like 'secret' are illustrative of naming conventions, not hardcoded credentials.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill mentions standard, reputable formatting tools (Prettier, ESLint, Black, isort). There are no commands that download and execute arbitrary scripts from untrusted sources.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill is designed to process code files (untrusted data) using Read, Grep, and Glob tools, it does not involve unsafe interpolation of this data into instructions that could lead to unintended agent actions.
Audit Metadata