The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were detected. The skill performs its primary function by analyzing local project assets such as index.tsx, spec.md, and screenshots to produce a documented PRD. All file operations are restricted to the local project environment.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from source code and documentation. This surface is inherent to its primary documentation function. 1. Ingestion points: Reads local project files including index.tsx, spec.md, content.md, and screenshot.png. 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the analyzed file content. 3. Capability inventory: The skill utilizes file system read and write capabilities within the project directory to generate prd.md. 4. Sanitization: No specific filtering or sanitization steps are defined for the content extracted from project files.

prd-generator