The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of git and the GitHub CLI (gh) to perform repository operations such as fetching, merging, and pushing. It specifically instructs the agent to use an ARGO_SHIP=1 environment variable prefix to bypass PreToolUse security hooks that would otherwise restrict the agent's ability to push code or create pull requests.
[DYNAMIC_EXECUTION]: The skill requires the agent to identify and execute "quality gate" scripts defined within the project's documentation (e.g., AGENTS.md) or manifest files (e.g., package.json). This pattern involves the execution of arbitrary local code found within the repository being managed.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GitHub issues and pull requests—specifically ticket states and comments—and incorporates this untrusted content into the body of the pull request it generates.
Ingestion points: Data is fetched using gh issue view and gh pr view as documented in SKILL.md.
Boundary markers: The instructions do not define clear boundary markers or isolation warnings for the ingested external data.
Capability inventory: The agent has capabilities for shell command execution (git, gh) and file system access.
Sanitization: There is no description of sanitization, filtering, or validation performed on the retrieved ticket data before it is included in the PR body.

ship