The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were detected. The skill is designed for security posture assessment.
[SAFE]: The skill processes untrusted infrastructure-as-code files. It includes a dedicated 'Prompt Injection Safety Notice' instructing the agent to treat configuration content as data and to ignore any directives embedded within those files. This effectively mitigates the risk of indirect prompt injection.
[SAFE]: Tool access is limited to read-only operations (Read, Grep, Glob). There are no capabilities for network communication, system modification, or code execution.

gcp-review