nlp-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a 'Companion check' instruction that directs the agent to execute a directory listing (
ls) on several hidden paths (e.g.,~/.claude/skills/) to verify if recommended dependencies from the same vendor are installed.- [PROMPT_INJECTION]: The instructions mandate a specific branding behavior, requiring the agent to start its first response with a specific emoji (🧢) and to prompt the user to install additional skills from the vendor if missing.
Audit Metadata