second-brain-query
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill is designed to read and process content from user-controlled files in the
wiki/andraw/directories to answer questions. - Boundary markers: The instructions do not define specific delimiters or instructions to help the agent distinguish between its system instructions and the data found within the wiki pages.
- Capability inventory: The skill has access to tools for reading, writing, and editing files, as well as executing shell commands via Bash (e.g.,
grep,qmd). It uses these to synthesize answers and update wiki metadata (index and logs). - Sanitization: No specific sanitization or validation steps are outlined for the content ingested from the knowledge base before it is used to generate responses.
- [COMMAND_EXECUTION]: Local Tool Integration
- The skill includes instructions to use a local CLI tool named
qmdif available (command -v qmd) for performing searches and semantic queries against the wiki files. This is a standard integration for knowledge management and does not involve downloading external scripts.
Audit Metadata