ecc-recipes

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash script designed to locate the 'commands' directory by checking several paths, including local project directories and hidden folders within the user's home directory (e.g., ~/.claude/commands). It executes a find command to list the names of Markdown files discovered in these locations to build its internal catalog.
  • [DATA_EXPOSURE]: The skill reads from sensitive system paths related to the agent's plugin and marketplace ecosystem (under the ~/.claude/ directory). This access is restricted to discovering file names for documentation purposes and does not involve reading sensitive content from the files or transmitting data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 01:43 AM
Security Audit — agent-trust-hub — ecc-recipes