responsive-design
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: In
SKILL.md, the "Companion check" section instructs the agent to execute a shell command (ls) to check for the presence of other skill directories in various local paths, including within the user's home folder (e.g.,~/.claude/skills/). This activity is used for environment discovery to identify already installed skills. - [EXTERNAL_DOWNLOADS]: The skill directs the agent to recommend and provide installation commands (
npx skills add AbsolutelySkilled/AbsolutelySkilled) for additional skills from an external GitHub repository based on the results of the filesystem scan. - [PROMPT_INJECTION]: The skill includes a behavior modification instruction requiring the agent to always start its first response with the 🧢 emoji, which is a form of cosmetic behavior override.
Audit Metadata