The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-provided documentation, markdown files, and code examples. This creates an indirect prompt injection surface where instructions hidden within the data being analyzed could attempt to influence the agent's behavior.
Ingestion points: Documentation files (docs/), examples, docstrings in Python/Rust code, and repository entry points (README.md, index.yml) identified during the Review Flow.
Boundary markers: None specified; the skill does not explicitly instruct the agent to use delimiters to separate user content from its own instructions.
Capability inventory: The skill mentions running repository-local tools like just docs and execution of scripts such as scripts/generate_api_docs.sh and scripts/docs/generate_rust_library_reference.py for API documentation generation and validation.
Sanitization: The skill does not provide explicit sanitization or filtering logic for external content, relying instead on the agent's standard safety protocols.
[COMMAND_EXECUTION]: The skill references local build and documentation tools, including just docs and specific shell/Python scripts within the scripts/ directory. These are presented as standard development workflow commands for maintaining the repository's documentation integrity and are not associated with arbitrary or remote command execution.

review-doc-style