research
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to create a directory structure (
mkdir -p docs/research) for storing research documents. This is a legitimate and safe use of the command line for file organization. - [EXTERNAL_DOWNLOADS]: The skill retrieves information from the web using
WebSearchandWebFetch. It specifically targets well-known and trusted platforms like official technical documentation and Stack Overflow to ensure data quality and relevance. - [DATA_EXFILTRATION]: No data exfiltration detected. The skill's primary function is to write research findings to local markdown files within the user's project directory.
- [INDIRECT_PROMPT_INJECTION]: As the skill processes untrusted content from the web, it has a potential exposure to indirect prompt injection. However, the risk is mitigated by explicit instructions for the AI to follow a strict markdown schema and perform specific string sanitization (lowercase conversion, character removal) when generating filenames.
Audit Metadata