react-single-responsibility
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to simplify and refactor React and TypeScript code, requiring it to read and edit user-provided source files (*.tsx, *.ts). This creates a vulnerability surface for indirect prompt injection, where instructions embedded within analyzed code could potentially influence agent behavior.\n
- Ingestion points: Ingests external source code for components, hooks, and methods via file system tools.\n
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are established to isolate untrusted code content from agent logic during processing.\n
- Capability inventory: The skill is granted permissions to use file system tools (Read, Write, Edit, Grep, Glob), enabling automated modifications to the codebase based on analysis of user content.\n
- Sanitization: The instructions do not define sanitization or validation procedures for code content prior to its use in the refactoring process.\n- [SAFE]: The skill recommends the use of industry-standard, well-known libraries such as react-hook-form and TanStack Query for managing state and data fetching.\n- [SAFE]: The architectural principles advocated (KISS, DRY, Single Responsibility) are recognized best practices that improve code security and maintainability.
Audit Metadata