The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute gh CLI commands and interact with the GitHub REST and GraphQL APIs. This is the primary functionality for automating repository management tasks.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from GitHub, specifically commit messages and issue bodies, to automate sub-task completion and generate session summaries.
Ingestion points: Commit messages and issue descriptions are read into the agent context via gh issue view, gh api, and specialized hooks.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the processed GitHub content.
Capability inventory: The skill utilizes Bash (for gh commands), Write, and Edit (to update issue bodies), which creates an attack surface where malicious instructions in a commit message could influence agent actions.
Sanitization: No explicit sanitization, validation, or escaping of external content is described before the data is used in automated updates.

github-operations