prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform a directory listing using the
lscommand on specific paths (e.g.,~/.claude/skills/,~/.agent/skills/) to determine if recommended companion skills are present. - [EXTERNAL_DOWNLOADS]: If recommended companion skills are missing, the agent is directed to suggest their installation from the vendor's repository using the
npx skills addcommand targetingAbsolutelySkilled/AbsolutelySkilled.
Audit Metadata