hig-foundations
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown documentation files that provide design principles and platform conventions. No malicious behavior, prompt injections, or exfiltration patterns were detected.
- [NO_CODE]: There are no scripts, package manifests, or executable binaries included in the skill.
- [INDIRECT_PROMPT_INJECTION]: The instructions suggest checking for a local context file (.claude/apple-design-context.md). Although this represents a potential surface for data ingestion, the skill lacks any capabilities (such as command execution or network access) that could be leveraged for an attack, rendering the surface benign.
Audit Metadata