The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user feature descriptions and PRD files to generate issues and update project documentation, creating a surface for injection. * Ingestion points: Untrusted data enters the agent context via feature descriptions provided by the user and existing PRD files located in the docs/prd/ directory (SKILL.md, REFERENCE.md). * Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when interpolating ingested data into outputs. * Capability inventory: The skill utilizes command-line tools like gh and glab for issue publishing and performs local file writes to update PRD status (REFERENCE.md). * Sanitization: The skill does not perform explicit sanitization, validation, or filtering of the external content before it is included in the new issues or project documentation.

story