system-design

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The 'Companion check' section in SKILL.md contains instructions for the AI agent to execute a shell command (ls) on the local machine upon activation. The command scans several hidden directories (e.g., ~/.claude/skills/, ~/.agent/skills/) to identify which other skills from the same author are installed.
  • [EXTERNAL_DOWNLOADS]: Based on the results of the filesystem scan, the skill directs the agent to suggest that the user download and install additional remote code via the npx skills add AbsolutelySkilled/AbsolutelySkilled command. This represents an automated 'upsell' mechanism that utilizes local system information.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:05 PM
Security Audit — agent-trust-hub — system-design