lov-branding-consistency
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [PERSISTENCE]: The
scripts/profile_store.pyscript manages a local JSON profile to store user preferences and brand facts. It includes an explicit safety filter (SENSITIVE_PARTS) that prevents the persistence of secrets, tokens, or credentials, ensuring that only non-sensitive branding data is stored.- [COMMAND_EXECUTION]: The skill's Python scripts facilitate local administrative tasks like auditing copy and syncing dependencies within the developer's ecosystem. These scripts utilize standard library functions for file system interactions and do not perform any network operations or dangerous command injections.- [DYNAMIC_EXECUTION]: All YAML parsing within the diagnostic and maintenance scripts is performed usingyaml.safe_load(), mitigating the risk of arbitrary code execution through malicious YAML payloads.- [DATA_EXPOSURE]: The skill contains a 'Visibility Firewall' core rule and an automated auditor (scripts/copy_audit.py) specifically designed to detect and remove production-related metadata from audience-facing copy, preventing accidental leaks of internal instructions.
Audit Metadata