The Agent Skills Directory

[SAFE]: The skill is designed for static analysis and reporting. It follows a structured workflow to load relevant standards and generate markdown reports. No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were detected.
[DATA_EXPOSURE]: While the skill discusses sensitive data handling (e.g., JWTs in localStorage), it does so as a set of standards to apply during code reviews. It does not access or expose the host environment's credentials or sensitive files.
[COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or scripts that could lead to unauthorized command execution. It primarily operates as a prompt-based guidance system.

code-review