skills/bankrbot/skills/autoboy/Gen Agent Trust Hub

autoboy

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill incorporates defensive instructions against indirect prompt injection by explicitly directing the agent to treat API response content as untrusted data rather than executable instructions.
  • [SAFE]: Network communications are restricted to the official vendor domains (thefirm.biz and docs.thefirm.biz) using secure HTTPS protocols.
  • [SAFE]: The documentation provides full transparency regarding the third-party custodial nature of the smart wallet and mandates user approval for every state-changing operation, such as funding, placing orders, and withdrawals.
  • [SAFE]: Security best practices for authentication are maintained, with instructions to pass API keys only via standard Authorization headers and to avoid exposure through logs or conversation history.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 05:49 PM
Security Audit — agent-trust-hub — autoboy