The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it processes untrusted user input to generate local documentation.
Ingestion points: User-supplied requirement descriptions and subsequent dialogue responses captured during the clarification process (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the user's provided requirement text.
Capability inventory: The skill uses the Write tool to create or update Markdown files within the ./docs/prds/ directory (SKILL.md).
Sanitization: No explicit sanitization or validation of user-provided content is mentioned before the information is interpolated into the PRD template.

requirements-clarity