create-skill

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains purely instructional content and templates designed to guide the agent and user through the process of creating modular instruction sets (skills) for the Zed environment.
  • [NO_CODE]: No executable scripts, shell commands, or external dependencies are included in the skill body or frontmatter.
  • [PROMPT_INJECTION]: The instructions are clear, helpful, and do not attempt to override system safety guidelines or agent behavior beyond their intended purpose of skill creation.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration patterns were detected. The paths referenced (~/.agents/skills/) are standard local configuration directories for the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 12:37 AM
Security Audit — agent-trust-hub — create-skill