whatsapp-styler-hardened
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard formatting instructions for WhatsApp usage, focusing on visual styling and clean mobile readability.
- [SAFE]: Security guardrails are implemented as natural language instructions to mitigate social engineering risks (impersonation) and prevent formatting errors when the agent is used in non-WhatsApp contexts.
- [SAFE]: External links in the documentation point to the author's official domains and repositories (faberlens.ai, github.com/faberlens), which are consistent with the skill's stated purpose of providing hardened formatting rules.
- [SAFE]: The inclusion of adversarial test cases in the safety documentation is for evaluative purposes and does not represent an attempt to exploit the system.
Audit Metadata