The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external pull requests which could contain adversarial instructions.
Ingestion points: The skill fetches data using gh pr view, gh pr diff, and GitHub API endpoints, retrieving PR titles, bodies, and code changes (SKILL.md).
Boundary markers: The instructions do not define explicit delimiters or instructions to the agent to treat the PR content as untrusted data or to ignore embedded commands.
Capability inventory: The skill utilizes git and gh CLI tools for repository management and PR metadata retrieval.
Sanitization: No sanitization or filtering is applied to the retrieved PR data before it is analyzed by the agent.
[COMMAND_EXECUTION]: The skill uses local CLI tools to perform its tasks.
Execution patterns: It executes git rev-parse, git fetch, git merge-base, and various gh pr commands to interact with the local repository and the GitHub API.
Context: The usage of these tools is consistent with the skill's stated purpose of reviewing pull requests.

pr-review