react-native-unistyles-v3
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a documentation and support tool for the react-native-unistyles library. All identified external resources, including NPM packages (react-native-unistyles, react-native-nitro-modules) and GitHub issue references, are standard dependencies or official support channels for the library. No malicious code, credential harvesting, or suspicious network activities were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a standard attack surface common to developer-oriented coding assistants.
- Ingestion points: The skill instructions direct the agent to read user source code via Read, Grep, and Glob tools in its primary workflow.
- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the user's code files.
- Capability inventory: The skill has access to Write and Edit tools for modifying code, as well as Bash(npx *) for project tasks such as installing pods or running the application.
- Sanitization: No specific sanitization or filtering logic is prescribed for the data read from user files.
- Assessment: This surface is consistent with the primary purpose of the skill as a coding assistant and does not indicate malicious intent or an unusual security risk.
Audit Metadata