The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which may contain adversarial instructions intended to influence the agent's behavior.
Ingestion points: The skill reads relevant product decisions, repository code, existing issues, pull requests, and live issue bodies/comments to ground its requirements gathering (Workflow steps 1, 2, and the 'Updates and Planning' section in SKILL.md).
Boundary markers: There are no explicit instructions to use prompt delimiters or boundary markers when interpolating this external content into the model's context.
Capability inventory: The skill has the authority to create or modify tracker issues and local documents, and it delegates tasks to other functional skills like writing-plans and prd-quality-gate (SKILL.md).
Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from external repository sources.

prd-writer