The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard development tools to perform repository operations, including git for commit verification and rebasing, gh (GitHub CLI) for pull request creation and state management, and pnpm for running build and test scripts.
[INDIRECT_PROMPT_INJECTION]: The skill relies on external repository files such as AGENTS.md and SECURITY.md to guide its procedures. This creates a surface where instructions embedded in those repository files could influence the agent's behavior during the PR creation process.
Ingestion points: AGENTS.md, SECURITY.md, and individual SKILL.md files within the repository.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded prompts in the ingested files.
Capability inventory: The agent has shell access to execute git, gh, and pnpm commands.
Sanitization: No sanitization or validation of the content read from the repository files is mentioned.

meta-pr-creation