The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data including pull request templates and branch content, creating a surface for indirect instructions.\n- Ingestion points: Ingests branch data, commit messages, and repository-native pull request templates to fulfill user requests (SKILL.md).\n- Boundary markers: No specific boundary markers or instructions to treat external data as untrusted text are provided in the alias instructions.\n- Capability inventory: Relies on the capabilities of the 'pr-writer' skill, which typically requires git write and file system read access.\n- Sanitization: The instructions do not define any sanitization or validation steps for the content extracted from the repository.

create-pr