The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local script scripts/install-external-skills.py to install supplementary capabilities. This is a standard setup procedure within the repository's architecture.
[PROMPT_INJECTION]: The skill processes untrusted external content from pull requests, creating a potential surface for indirect prompt injection. Ingestion points: PR descriptions, existing comments, and code diffs. Capability inventory: Uses git tools to read repository state and generates markdown reports. Boundary markers: No specific delimiters or isolation instructions are provided for external content. Sanitization: No explicit sanitization of the input data is mentioned.

code-review