The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the React project files it audits, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: The skill scans the entire project structure, reading file names and contents across the src/ directory, including package.json, src/routes.tsx, store slices, and component files. It also reads DESIGN.md from the project root.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between its auditing instructions and the content of the files it is reading.
Capability inventory: The skill possesses extensive file-reading capabilities and the ability to write to the file system (specifically copying a DESIGN.md file to the project root).
Sanitization: The instructions do not include any guidance for sanitizing or escaping content read from the files before it is used to generate the audit report.

react-architect