ClawHub
Back to skill

Security audit

Gate Pay Payment Skill

Security checks across malware telemetry and agentic risk

Overview

This Gate Pay skill is transparent about making payments, but it deserves review because it can make irreversible charges and uses broad activation language plus mutable external runtime rules.

Review before installing. Use it only for trusted Gate Pay merchant orders, verify the exact order ID, amount, currency, merchant context, and Gate Pay account before allowing payment, and be aware that the skill relies on external Gate runtime-rule links that are not pinned inside the package.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are broad enough to match common conversational payment language such as 'pay', 'checkout', or 'complete payment', which creates a real risk of unintended skill activation in unrelated contexts. In a payment-execution skill, accidental invocation is especially dangerous because it can steer the agent into preparing or executing an irreversible financial action based on ambiguous user input or stale context.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The manifest description uses broad trigger phrases such as 'complete payment' and 'pay for order', which can cause the skill to activate on ambiguous user requests. In a payment-execution skill with an irreversible write action, over-broad routing increases the chance of unintended invocation and downstream charging if the orchestrator relies heavily on manifest text for selection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.