The Agent Skills Directory

[SAFE]: The skill's primary function is text processing and local file writing within a designated documentation directory.
[SAFE]: No network activity, external downloads, or execution of arbitrary code were detected.
[SAFE]: Filename generation for PRDs involves a kebab-case transformation, which acts as a basic sanitization measure against path traversal.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted user requirements and interpolates them into generated PRDs. This is inherent to the skill's purpose and handled safely within the local environment.
Ingestion points: User requirement descriptions provided during the initial analysis and subsequent clarification rounds.
Boundary markers: Information is organized into structured markdown headers and sections in the final output.
Capability inventory: Uses the Write tool to create and modify files in the ./docs/prds/ directory.
Sanitization: Transforms feature names into kebab-case for file paths, though it does not explicitly filter content for embedded instructions.

requirements-clarity