The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface because it processes untrusted data from the conversation history and repository files to generate a PRD that is then published via the gh tool.
Ingestion points: Ingests the current conversation context, repository codebase structure, AGENTS.md, and issue templates.
Boundary markers: No delimiters or instructions are used to separate user-provided content from the skill's logic.
Capability inventory: Employs the GitHub CLI (gh) to publish issues to the project's tracker.
Sanitization: The skill does not specify any sanitization, escaping, or validation of the processed data before it is sent to the issue tracker.
[COMMAND_EXECUTION]: The skill relies on the gh command-line utility to interact with the repository's issue tracker. This usage is aligned with the skill's stated purpose and uses official project tooling.

to-prd