community-management
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to run a shell command (
ls) to inspect various hidden directories within the user's home folder (such as~/.claude/skills/,~/.agent/skills/, and~/.agents/skills/). This is used to perform a 'companion check' to identify other installed skills. - [PROMPT_INJECTION]: The skill includes instructions that override standard agent behavior, such as mandating that every first response begins with a specific emoji (🧢) and requiring the agent to automatically perform filesystem inspection upon activation.
- [EXTERNAL_DOWNLOADS]: The documentation and skill instructions recommend downloading and installing additional code packages from the AbsolutelySkilled GitHub repository using the
npx skillscommand.
Audit Metadata