react-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The file 'references/rules/download_rules.sh' utilizes 'curl' to retrieve markdown documentation from 'https://raw.githubusercontent.com/vercel-labs/agent-skills/'. Under the [TRUST-SCOPE-RULE], the severity is downgraded to LOW as the destination is a Trusted GitHub Repository.
- [PROMPT_INJECTION] (LOW): The skill possesses a Category 8 (Indirect Prompt Injection) vulnerability surface. 1. Ingestion points: The skill is designed to ingest and refactor untrusted user-provided React components and project files. 2. Boundary markers: The skill does not implement delimiters or warnings to ignore instructions within processed data. 3. Capability inventory: The skill contains a shell script capable of network operations and file writing. 4. Sanitization: No sanitization or validation of the processed user code is performed.
- [SAFE] (SAFE): The architectural patterns and optimization rules provided (such as parallel fetching and bundle optimization) are standard industry best practices. No evidence of obfuscation, hardcoded credentials, or persistence mechanisms was found in the analyzed files.
Audit Metadata