The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub Pull Requests which can be used to influence the agent's behavior.
Ingestion points: The skill fetches the PR body, diff, and existing comments using gh pr view, gh pr diff, and gh api calls in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to help it distinguish between the PR content and its own system instructions.
Capability inventory: The agent has the ability to execute shell commands (gh CLI) and perform network write operations (gh api ... --method POST) to submit reviews and comments.
Sanitization: The instructions do not mention any sanitization or filtering of the content retrieved from the PR before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the gh (GitHub CLI) to perform all repository and API operations. While these are standard tools for the task, they represent the execution of shell commands based on inputs derived from the PR URL provided by the user.

review-pr