The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the GitHub CLI (gh) for issue management, check for local configuration files with ls, and install skills via `npx".
[EXTERNAL_DOWNLOADS]: Fetches setup scripts and packages from well-known services like "astral.sh" (for Python environment management) and the npm registry for vendor-specific packages.
[REMOTE_CODE_EXECUTION]: References a remote script execution pattern ("curl | sh") in "references/DEV_SETUP.md" for installing the "uv" tool. This originates from a well-known service and is presented to the user for manual confirmation.
[PROMPT_INJECTION]: Contains an indirect prompt injection surface where the agent processes external data from GitHub issues (ingestion point in "SKILL.md").
Ingestion points: GitHub issue summaries and descriptions fetched via "gh search issues".
Boundary markers: No explicit delimiters are used to wrap external content.
Capability inventory: The skill has access to the "Bash" tool and can perform GitHub operations.
Sanitization: Instructions explicitly direct the agent to summarize the external content rather than providing raw output, providing a natural barrier against malicious instructions.

contributor