agent-guardrails

Warn

Audited by Snyk on Jun 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill explicitly references financial actions: it notes agents may have tools that "touch ... money" and the example tool-gate lists a "refund" tool (HITL_REQUIRED = {"refund", "delete_user"}). "refund" is a specific financial operation (moving funds back to a user), so the skill includes a tool explicitly designed for financial execution (even if human approval is required). Therefore it grants direct financial execution capability.

Issues (1)

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 27, 2026, 04:56 PM
Issues
1
Security Audit — snyk — agent-guardrails