partner-google
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of informational content and stylistic instructions for the agent. No executable scripts or system commands are present.
- [SAFE]: References to local file paths and private documentation (e.g., in the .frankx/private directory) are provided as contextual cross-references and do not include instructions for unauthorized access or data exfiltration.
- [SAFE]: Integration patterns described in the text (such as deriving file extensions from MIME types) are logical guidelines for the agent to follow when generating code, rather than malicious code themselves.
- [SAFE]: The 'Voice rules' section contains standard stylistic constraints (e.g., avoiding specific buzzwords) to define the agent's persona and does not attempt to bypass safety filters or override system constraints.
Audit Metadata