The Agent Skills Directory

[SAFE]: The skill defines a set of high-quality instructions for code analysis. It explicitly instructs the agent to look for security vulnerabilities such as SQL injection, command injection, and hardcoded credentials in the target code.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it is designed to read and process external Python files provided as arguments. However, this is inherent to the purpose of a code review skill. The risk is minimized as the skill focuses on reporting findings rather than executing the code or performing sensitive operations based on the file content.

review