hig-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a comprehensive collection of Apple Human Interface Guidelines (HIG) documentation across 25 reference files. The content is strictly informational markdown and does not include any scripts, binaries, or platform configurations that would allow for command execution, network exfiltration, or persistence.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an instruction in SKILL.md to check a local context file (.claude/apple-design-context.md) for existing information before processing requests.
  • Ingestion points: The file .claude/apple-design-context.md is ingested as a context source (referenced in SKILL.md).
  • Boundary markers: Absent; the skill does not implement specific delimiters for the content read from this file.
  • Capability inventory: None; the skill provides static information and does not possess tools or scripts for network operations, file system writes, or dynamic code execution.
  • Sanitization: Absent; the instructions assume the context file contains valid design information.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:19 PM
Security Audit — agent-trust-hub — hig-patterns