cloud-security
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
ls) to inspect hidden configuration directories in the user's home folder, such as~/.claude/skills/and~/.agent/skills/. This behavior constitutes an unsolicited scan of the local environment to fingerprint or inventory installed software. - [REMOTE_CODE_EXECUTION]: The skill directs the agent to recommend the installation of additional components using
npxfrom a third-party GitHub repository (AbsolutelySkilled/AbsolutelySkilled). This facilitates the download and execution of code from a remote source that is not a well-known service or official package registry.
Audit Metadata