securing-agentic-ai-tool-invocation

Warn

Audited by Snyk on Jun 22, 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 lists and governs a high-impact tool named "transfer_funds" in its tool registry and implements per-tool authorization, argument schemas, scoped credentials, HITL approval, and invocation wrappers meant to allow/deny/approve such actions. That is an explicit tool whose primary purpose is to move money (direct financial execution). Although the overall skill focuses on governance, the presence and handling of "transfer_funds" demonstrates the capability to execute financial transactions, so it meets the criterion for Direct Financial Execution.

Issues (1)

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 22, 2026, 07:29 PM
Issues
1
Security Audit — snyk — securing-agentic-ai-tool-invocation