team-builder
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill operates by discovering and executing agent persona definitions from local markdown files within the
./agents/directory. - Ingestion points: The skill performs recursive directory globs on
./agents/to find and read markdown file content (Steps 1 and 4). - Boundary markers: No explicit sanitization or instructions to ignore embedded prompts within the persona files are mentioned.
- Capability inventory: The skill is designed to spawn parallel agent instances and provide a synthesized report of their outputs.
- Sanitization: No specific filtering is applied to the markdown content before it is used to define agent behavior. This is an inherent part of the skill's design for managing local agent configurations.
Audit Metadata