The Agent Skills Directory

[SAFE]: The skill primarily consists of educational content and best practices for code quality and security. It encourages safe practices such as parameterized SQL queries and avoiding hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data from pull requests, representing a potential surface for indirect prompt injection. 1. Ingestion points: The review process involves reading pull request descriptions, linked issues, and code changes as described in SKILL.md. 2. Boundary markers: The instructions do not define specific delimiters or clear instructions for the agent to treat ingested code strictly as data. 3. Capability inventory: A local script scripts/pr-analyzer.py is referenced, and the agent typically has file system and shell capabilities. 4. Sanitization: No specific input sanitization or validation steps are provided for the processed content.

code-review-excellence