color-theory
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 execute shell commands (
ls) to inspect multiple directories (e.g.,~/.claude/skills/,~/.agent/skills/,.agents/skills/) to identify which companion skills are installed. This allows the agent to fingerprint the local environment and its capabilities. - [EXTERNAL_DOWNLOADS]: The instructions prompt the agent to suggest installing additional remote skills (such as
design-systemsandultimate-ui) from theAbsolutelySkilledorganization using thenpx skills addcommand if they are not detected locally.
Audit Metadata