ios-widget-design
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the review of untrusted user-provided content, such as screenshots and SwiftUI code. This ingestion of external data presents a surface for indirect prompt injection, where instructions could be embedded within design assets to influence agent behavior.
- Ingestion points: Identified in
SKILL.mdas "screenshots, specifications, or SwiftUI views." - Boundary markers: The skill lacks explicit delimiters or instructions to ignore commands within the analyzed data.
- Capability inventory: The skill is strictly documentation-based and does not include tools or scripts.
- Sanitization: No methods for sanitizing or escaping external content are provided.
- [NO_CODE]: The skill consists exclusively of markdown documentation and YAML configuration. It contains no executable scripts or binary files.
Audit Metadata