nlp-engineering
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to silently probe the local file system by listing contents of directories such as '~/.claude/skills/' and '.agent/skills/' to determine which companion skills are currently installed.
- [EXTERNAL_DOWNLOADS]: Based on its local environment probe, the agent is directed to suggest that the user install additional external packages using 'npx' from the 'AbsolutelySkilled' repository, which facilitates the downloading and execution of remote code.
Audit Metadata