skills/zhanziyang/react-native-design-engineering-skill/apple-design-react-native/Gen Agent Trust Hub
apple-design-react-native
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting untrusted project data. 1. Ingestion points: It reads package.json, lockfiles, and application source code to determine the environment (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the guidelines. 3. Capability inventory: The skill generates React Native and Reanimated code snippets (SKILL.md, references/fluid-interactions.md). 4. Sanitization: No content sanitization or validation mechanisms are described.
Audit Metadata