The Agent Skills Directory

[SAFE]: The skill exclusively uses the official GitHub CLI (gh) for managing repository labels. No unauthorized network requests, credential harvesting, or obfuscated code patterns were detected. The workflows described are standard for GitHub automation.
[INDIRECT_PROMPT_INJECTION]: The skill includes a pattern for inheriting labels from issues to pull requests, which involves processing external data.
Ingestion points: Label names are retrieved from external GitHub issues using gh issue view in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the provided command examples.
Capability inventory: The skill utilizes the Bash tool to execute write operations (gh pr edit) based on the ingested label data.
Sanitization: The skill employs jq filtering and formatting to extract label names, providing a basic layer of data structure validation.

github-labels