The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the gh CLI for repository operations. In CREATE_ISSUE.md, it also performs dynamic context injection by executing a shell command (node -p) to retrieve system temporary directory paths and timestamps for file management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and displays content from external GitHub issues and comments which may contain malicious instructions.
Ingestion points: Data is read from the GitHub API via gh issue view and gh issue list as documented in VIEW_ISSUE.md and LIST_ISSUES.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched content as untrusted or to ignore embedded instructions.
Capability inventory: The skill possesses the ability to write to the local filesystem (Write tool) and modify remote repository states (creating, editing, and closing issues).
Sanitization: No sanitization or validation logic is defined to inspect or clean the retrieved issue content before it enters the agent's context.

github