team-list
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local files, which could contain instructions intended to influence agent behavior.
- Ingestion points: The skill uses a Glob tool to find and a Read tool to parse all .yaml files in the .team-profiles/ directory.
- Boundary markers: Content from the files is directly interpolated into the output without using delimiters or system-level instructions to ignore embedded commands.
- Capability inventory: Analysis of the skill body and scripts confirms the use of file system read tools (Glob, Read) but identifies no high-risk capabilities such as network access, file writing, or subprocess execution.
- Sanitization: The skill truncates the team description to 40 characters, which provides a physical limit to potential injection payloads but does not involve active sanitization or escaping of the content.
Audit Metadata