The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and process React source files, which creates a potential surface for indirect instructions to be passed to the agent.
Ingestion points: The agent identifies and processes files matching the **/*.tsx and **/*.jsx patterns as specified in the skill's triggers.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers for the agent to use when reading third-party code.
Capability inventory: No dangerous tools or capabilities (such as shell execution, network access, or file system writes) are requested in the skill's configuration.
Sanitization: There is no instruction for the agent to sanitize or validate the content of the React files before analysis.
[EXTERNAL_DOWNLOADS]: The skill provides a reference link to a specialized implementation pattern for React hooks.
Reference: The implementation guidelines link to an external resource at https://react.gg/hooks/use-latest-ref. This is a well-known educational site for React developers and is documented here for completeness.

react-hooks