The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were found. The skill instructions focus on legitimate development and code review workflows.
[DATA_EXPOSURE]: The skill mentions sensitive configuration files like .env and variables such as JWT_SECRET, but only to provide instructions on securing them and ensuring they are not committed to version control, which is a security best practice.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review code provided in the agent's context. While this represents a data ingestion surface, the instructions focus on enforcing security and quality standards rather than executing untrusted logic, posing minimal risk.
[COMMAND_EXECUTION]: The skill mentions standard development commands such as npm run build and npx prisma migrate. These are presented as user instructions for local development workflows and do not involve silent or malicious execution.

generic-fullstack-code-reviewer