Security audit

汇付支付历史最强 Doctor：基于证据的支付诊断手册 (让你的AI不再胡思乱想）

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable Huifu payment troubleshooting guide that handles sensitive diagnostics but tells users to redact secrets and does not perform payment actions.

Before installing or using this skill, treat payment logs and webhook payloads as sensitive. Redact private keys, certificates, tokens, passwords, full card or identity numbers, customer personal data, and unnecessary merchant identifiers. Use it as a troubleshooting checklist, and verify production-impacting changes against official Huifu/DouGong documentation or support.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill enables allow_implicit_invocation without defining any activation constraints or trigger phrases, so the agent may invoke this payment-diagnostics skill in contexts the user did not explicitly request. Because the skill is designed to steer troubleshooting behavior and may cause the model to request or rely on sensitive logs, request/response payloads, webhook traces, and merchant configuration, unintended invocation can expose sensitive financial integration data or alter assistant behavior unexpectedly.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.