creating-skills

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes several TypeScript utility scripts (init-skill.ts, package-skill.ts, validate-skill.ts) designed to be executed via npx (using ts-node or tsx). These scripts perform necessary file system operations such as directory creation, file reading/writing, and file permission adjustments (chmod 755) to facilitate the skill development lifecycle.
  • [EXTERNAL_DOWNLOADS]: The documentation references agentskills.io as an external resource for the official specification. This is a legitimate documentation link and does not involve automated downloads or remote code execution.
  • [DATA_EXFILTRATION]: The packaging script (package-skill.ts) reads files within the local skill directory to create a compressed .skill (ZIP) archive for distribution. This behavior is consistent with the skill's stated purpose of managing and packaging development assets.
  • [SAFE]: All identified behaviors, including the use of local utility scripts and references to external documentation, are aligned with the intended purpose of a developer tool for creating AI agent extensions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 03:25 PM