creating-skills

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Command Execution] (SAFE): The scripts init-skill.ts, package-skill.ts, and validate-skill.ts are local development utilities intended for execution via ts-node. They perform standard file system operations like creating directories and reading/writing local files.
  • [Dynamic Execution] (LOW): init-skill.ts generates a boilerplate TypeScript script and uses chmodSync to set executable permissions (0755). This is a standard and expected behavior for a project initialization tool.
  • [Metadata Poisoning] (SAFE): The validate-skill.ts script implements defensive checks on metadata, such as restricting the use of angle brackets (<, >) in descriptions and enforcing naming conventions, which mitigates risks associated with downstream rendering of skill data.
  • [Data Exposure & Exfiltration] (SAFE): No network operations (curl, fetch, etc.) or hardcoded credentials were found. The scripts interact exclusively with local file paths provided by the user via command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:19 PM