skill-creator

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and focused on content generation. It guides users through a structured dialogue to produce a markdown-formatted file (SKILL.md) based on their pedagogical expertise.
  • [PROMPT_INJECTION]: The skill includes specific steps (Step 5: Check Persona Compliance) to ensure that the generated instructions adhere to safety and educational constraints, mitigating the risk of creating harmful or non-compliant agent behaviors.
  • [DATA_EXFILTRATION]: No network operations, sensitive file access, or credential usage were detected. The skill's primary function is text generation and formatting.
  • [COMMAND_EXECUTION]: While the skill mentions placing files in a specific directory structure (skills/<persona>/<skill-name>/SKILL.md), it does not contain automated scripts or commands that execute without user oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 01:10 PM
Security Audit — agent-trust-hub — skill-creator