skill-create

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses several shell commands (Bash, Python, find, mkdir) to manage the local file system.
  • It uses find to locate instinct and cluster definitions in ~/.claude/instincts/.
  • It uses mkdir -p to create directory structures for new skills.
  • It executes small Python snippets to update YAML frontmatter in metadata files and generate unique identifiers (tokens and timestamps).
  • It performs collision checks before writing files to ensure it does not overwrite existing data.
  • These operations are limited to the user's ~/.claude/ directory and are essential for the skill's primary function of organizing and maturing agent behaviors.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 05:43 AM
Security Audit — agent-trust-hub — skill-create