instructor
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were found in the skill content.
- [EXTERNAL_DOWNLOADS]: The skill includes standard instructions to install the 'instructor' package, which is a well-known tool in the AI community.
- [PROMPT_INJECTION]: The skill processes LLM outputs which presents an indirect prompt injection surface. 1. Ingestion points: Data enters the context through LLM completion calls in SKILL.md. 2. Boundary markers: No explicit prompt delimiters are defined in the examples. 3. Capability inventory: No dangerous capabilities such as shell execution or file-system access are used. 4. Sanitization: The skill utilizes Pydantic models for strict schema enforcement and data validation.
Audit Metadata