apple-design
Fail
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains a reference to a malicious domain in
references/philosophy-and-evolution.md. The URLhttps://www.designzoo.co/p/how-apple-s-jony-ive-echoed-dieter-rams-10-principles-a-deep-divebelongs to a domain (designzoo.co) that is blacklisted by security scanners (URLite). Accessing this domain or fetching its resources may expose the environment to harmful content. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to process and restyle user-provided interface content according to specific design rules.
- Ingestion points: The agent ingests user-provided UI descriptions, restyling requests, and interface code as defined in
SKILL.md. - Boundary markers: The skill does not implement delimiters or safety warnings to distinguish between user data and the agent's internal instructions.
- Capability inventory: The skill is a documentation-based reference and does not contain scripts capable of subprocess execution, network writes, or file system modifications.
- Sanitization: There is no evidence of input validation or sanitization for the content processed by the agent.
Recommendations
- CRITICAL: 1 infected file(s) detected - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata