hig-components-controls
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of markdown documentation and instructional text for the AI agent. No malicious patterns, command executions, or data exfiltration attempts were detected.
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to check for a local context file (
.claude/apple-design-context.md). While this represents a data ingestion surface for potentially untrusted local content, the skill lacks any 'dangerous' capabilities (such as shell execution, file writing, or external network requests) that could be exploited via indirect injection.
Audit Metadata