1k-new-skill
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation from official Anthropic domains (code.claude.com and platform.claude.com) using the WebFetch tool to provide the agent with the most recent guidelines for skill creation.
- [COMMAND_EXECUTION]: Instructs the agent to perform routine file system and Git operations (ls, mkdir, mv, git commit) to organize skill directories and manage version control.
- [COMMAND_EXECUTION]: Executes a local Python utility (analyze-skills-tokens.py) to perform token analysis on newly created or modified skills, ensuring they remain within efficient size limits.
Audit Metadata