The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) and standard shell utilities (ls, cat, rm) to perform its primary functions. It executes commands to authenticate, list issues, create labels, and perform GraphQL API mutations. While these are legitimate developer tools, they represent an active command execution surface.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from local markdown files to populate GitHub issues. This surface is vulnerable to instructions embedded within the processed data.
Ingestion points: Files located at .claude/plans/*.md, plans/*.md, and prds/*.md are read and parsed.
Boundary markers: None identified. The content is directly interpolated into shell command templates for GitHub issue creation.
Capability inventory: Execution of GitHub CLI commands (including arbitrary GraphQL queries) and the ability to delete files (rm) upon user confirmation.
Sanitization: No explicit sanitization or validation of the markdown content is described before it is passed to the shell environment or the GitHub API.
[EXTERNAL_DOWNLOADS]: The skill references methodology from linear.app, which is a well-known project management service. This is a documentation reference and does not involve downloading or executing external code.

ralph-github-create-issues