markdown-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): No instructions designed to bypass agent constraints or safety protocols were detected.
- [DATA_EXFILTRATION] (SAFE): The skill does not access sensitive local files or perform unauthorized network requests. It focuses on local repository markdown files.
- [COMMAND_EXECUTION] (SAFE): Commands provided are standard utilities (
markdownlint,tr) used for documentation maintenance and file sanitization. - [REMOTE_CODE_EXECUTION] (SAFE): No instances of downloading or executing scripts from remote or untrusted sources were found.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill involves processing markdown files (ingestion point:
path/to/file.md), its primary purpose is structural linting rather than interpreting untrusted instructions.
Audit Metadata