tool-selector
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and YAML configuration that define a protocol for tool selection and planning. The logic promotes best practices such as caching and parallelization.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted task descriptions to generate execution plans. 1. Ingestion points: The Task summary field in the output format defined in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Guides usage of code execution, file writing, API calls, and database queries. 4. Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The skill documentation mentions npx skills add fatih-developer/fth-skills which is a management command for the vendor's ecosystem.
Audit Metadata