second-brain-query
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute 'qmd search', a command-line utility for searching the wiki. This operation uses user-provided query terms, which could pose a command injection risk if the agent does not properly sanitize the input.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes content from external files.
- Ingestion points: Content is retrieved from wiki/index.md, wiki/sources/, and raw/ directories.
- Boundary markers: No delimiters or isolation instructions are provided to separate file content from the agent's instructions.
- Capability inventory: The agent is equipped with Bash, Read, Write, Edit, Glob, and Grep tools.
- Sanitization: No sanitization is performed on the data retrieved from the wiki files before processing.
Audit Metadata