The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides documentation and code templates for React components that ingest and render external data (e.g., UserCard in conc-concurrent-safe.md, UserProfile in rsc-data-fetching-server.md, and ProductList in rstate-derived-values.md). These patterns create a surface for indirect prompt injection where untrusted data could potentially influence agent behavior if the rendered output is subsequently parsed by the AI.
Ingestion points: Multiple component templates designed to receive data via props or fetch operations.
Boundary markers: None present in the code examples to distinguish between instructions and data.
Capability inventory: The skill is documentation-based and does not contain scripts that execute code, though it describes patterns for network fetching and file system interaction (via server components).
Sanitization: Code examples do not demonstrate explicit sanitization or filtering of the external content before rendering.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install an external dependency to enable specific build-time optimizations.
Evidence: Recommends installing babel-plugin-react-compiler from the npm registry in references/memo-compiler.md using the command npm install --save-dev babel-plugin-react-compiler.

react