The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to facilitate the review and modification of React code, which constitutes an attack surface for indirect prompt injection if user-provided code contains malicious instructions.\n
Ingestion points: The agent reviews user-provided React components, hooks, and effects as specified in SKILL.md.\n
Boundary markers: There are no explicit instructions to treat user-provided code as untrusted or to ignore embedded natural language instructions within code comments or strings.\n
Capability inventory: The skill allows the agent to use Read, Write, Edit, Glob, and Grep tools, enabling it to modify the codebase based on its analysis.\n
Sanitization: There are no instructions for sanitizing or validating user-provided code before processing or writing to files.

react