The Agent Skills Directory

[SAFE]: No malicious patterns, security bypass attempts, or unauthorized access behaviors were detected. The skill's logic is consistent with its stated purpose of architectural auditing.
[NO_CODE]: This skill consists entirely of markdown instructions and YAML configuration. It does not include or execute external scripts, reducing the risk of traditional code-based vulnerabilities.
[DATA_EXPOSURE]: The skill instructs the agent to analyze codebase components such as API services, tool definitions, and data models. This data processing is necessary for the audit and remains within the agent's context; no exfiltration to external domains was identified.

agent-native-audit