The Agent Skills Directory

[SAFE]: The skill contains instructional content that encourages robust security practices, including the use of parameterized queries to prevent SQL injection and input sanitization to prevent cross-site scripting (XSS).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted source code and project configuration files as part of its core functionality. 1. Ingestion points: The agent is instructed to read code files, package manifests, and project-specific rule files such as CLAUDE.md. 2. Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from potentially following instructions embedded within comments or metadata of the code being reviewed. 3. Capability inventory: The agent typically has access to file system operations and terminal execution while performing these reviews. 4. Sanitization: No specific sanitization or filtering of the input source code is described in the skill.

generic-code-reviewer