The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from the Port service catalog, including service metadata and incident logs, which are then used to populate a PRD template.
Ingestion points: Port API results from get_entity and list_entities calls in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to distinguish between fetched data and prompt instructions.
Capability inventory: The skill uses run_action to write content to external work management systems like Jira or Linear.
Sanitization: Content fetched from the service catalog is interpolated into the PRD without explicit sanitization or filtering of external input.

generate-prd