The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources including URLs and pull request diffs. While this constitutes an ingestion point for untrusted data, the skill includes explicit instructions for the agent to verify the target's authenticity via project-specific markers and port auditing. This verification step effectively mitigates the risk of the agent acting on malicious or misleading external content.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool for repository introspection via the GitHub CLI and for validating network ports using lsof. These operations are strictly aligned with the skill's stated purpose of gathering design changes and verifying development environments, following the principle of least privilege for the intended task.

wk-design-review