The Agent Skills Directory

[SAFE]: The skill primarily serves as a reference for the gh command-line tool. All operations are conducted through the user's local gh installation, relying on standard GitHub authentication and authorization flows.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from GitHub (e.g., issue titles, PR descriptions) which could theoretically contain malicious instructions. However, this is a known risk for any tool interacting with user-generated content and is considered a baseline surface in this context.
Ingestion points: Data is retrieved via gh project item-list and gh issue list as documented in SKILL.md and references/items.md.
Boundary markers: The instructions do not define specific delimiters for separating ingested issue content from the agent's instructions.
Capability inventory: The skill provides access to gh project commands for managing project structure and content across all files.
Sanitization: There are no instructions for sanitizing or escaping the content retrieved from GitHub before it is processed by the agent.

github-projects