create-skill

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for standard shell commands such as mkdir, cat, and chmod to facilitate the initialization and configuration of skill directories and resource files.
  • [DYNAMIC_EXECUTION]: Instructions guide the agent to generate scripts (e.g., shell or Python) and execute them locally to verify their functionality as part of the skill development and testing process.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting user-provided examples and requirements to generate procedural instructions for new skills. This design creates a surface where the agent processes external data to influence the generation of new logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:24 PM
Security Audit — agent-trust-hub — create-skill