learn-investigate
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to read and process content from local project files and git history during its evidence collection phase.
- Ingestion points: Project source code and documentation accessed via Read and Grep tools, plus git history output.
- Boundary markers: No specific delimiters are defined to isolate external data from the agent's internal reasoning instructions.
- Capability inventory: The skill is authorized to use Bash, Write, Edit, Read, and request_user_input.
- Sanitization: There are no explicit instructions to sanitize or escape the content read from files.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git log and maestro CLI commands. The arguments for these commands are derived from search terms and file paths identified during the investigation. Potential risks are managed by a strict scope lock invariant that restricts the tool's access to user-defined directories.
Audit Metadata