The Agent Skills Directory

[SAFE]: The skill does not contain any prompt injection attempts or instructions meant to bypass safety filters or override agent behavior. The role definition is consistent with professional engineering guidance.- [SAFE]: No data exposure or exfiltration risks were identified. Code snippets use standard web APIs for demonstration purposes (e.g., fetch, localStorage) and do not access sensitive file paths like .ssh, .aws, or .env files.- [SAFE]: There are no obfuscation techniques present. All code and documentation are provided in clear, readable text without encoded strings, zero-width characters, or hidden payloads.- [SAFE]: All referenced external packages are industry-standard libraries for React development, such as Zustand, Redux Toolkit, and TanStack Query. No suspicious installation scripts or remote code execution patterns were found.- [SAFE]: Indirect prompt injection surface analysis: 1. Ingestion points: The skill processes user requirements for React application architecture (SKILL.md). 2. Boundary markers: The skill relies on standard markdown delimiters for code generation. 3. Capability inventory: The skill is limited to providing programming advice and code snippets. 4. Sanitization: Not applicable for this instructional skill.

react-expert