AGENT LAB: SKILLS

app-store-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill contains placeholder API key examples (e.g., 'sk_live_xxxxx') intended to teach the agent what to flag in user code; these are not actual credentials and do not pose a risk.
  • [Dynamic Execution] (SAFE): The skill documentation mentions 'eval' as a reason for App Store rejection but does not contain or execute any dynamic code itself.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external script downloads or remote code execution patterns were detected within the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:57 PM