The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data by providing templates for pull request creation, which constitutes a potential injection surface.
Ingestion points: The file references/pull-request.template.md defines placeholders such as {{ISSUE_NUMBER}}, {{NEW_FILE_OR_FEATURE}}, and {{BUG_DESCRIPTION}} which are intended to be filled with external content.
Boundary markers: No explicit boundary markers or delimiters are defined to separate untrusted content from the agent's instructions.
Capability inventory: The skill does not define any specialized tools, file-write capabilities, network operations, or shell execution commands, significantly limiting the impact of any potential injection.
Sanitization: The skill does not specify any sanitization or validation steps for the data processed by the templates.

git-workflow