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
Risk Level
SAFE
Analyzed
Apr 7, 2026, 08:10 PM