The Agent Skills Directory

[SAFE]: The skill provides legitimate documentation and code examples for SolidJS 2.0. It adheres to framework standards and incorporates security features such as CSRF origin checking, AbortController for managing network lifetimes, and explicit warnings against insecure server-side practices.\n- [INDIRECT_PROMPT_INJECTION]: The skill documents architectural patterns for handling external data streams, specifically WebSocket messages and server-side cookie decoding. These represent potential ingestion points for untrusted data that could influence an agent's behavior if processed within a high-capability environment.\n
Ingestion points: WebSocket message listener implementation in references/patterns.md; decodeFlashCookie and submission processing in references/server-functions.md.\n
Boundary markers: Not explicitly provided in the architectural reference snippets.\n
Capability inventory: The SKILL.md instructions guide the agent to perform project-level typechecks and execute runtime verification tests to validate code changes.\n
Sanitization: The provided code snippets focus on framework integration and do not include application-specific data sanitization or input validation logic.

solidjs-v2