The Agent Skills Directory

[SAFE] (SAFE): The skill provides documentation and code snippets for React functional components, custom hooks, and state management. No malicious patterns, obfuscation, or data exfiltration attempts were detected.
[Indirect Prompt Injection] (SAFE): The skill defines a surface for processing untrusted data by allowing tools to read and grep project files, which is necessary for its purpose as a development tool.
Ingestion points: The skill uses Read, Glob, and Grep tools to ingest content from the project directory.
Boundary markers: None are defined in the skill instructions to separate code from instructions.
Capability inventory: The skill allows Bash, Write, and Edit tools, which could be used to execute commands or modify files if the agent were manipulated.
Sanitization: No sanitization logic is provided within the skill itself, relying on the agent's core safety layers.

react