The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest external data from GitHub issues or local markdown files which introduces a vulnerability surface for indirect prompt injection. Ingestion points: Untrusted data enters the context through gh issue view commands and local file reads. Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the PRD text. Capability inventory: The skill has the ability to execute gh issue create and write markdown files to the local file system. Sanitization: The skill does not implement validation or escaping of the PRD content before interpolating it into issue templates.

prd-to-issues