CAI: settle-agent-invoice

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed CAI invoice-payment helper that is high-impact because it can guide transfers, but its artifacts require user confirmation and show no hidden code or automatic execution.

Install only if you intend to let an agent help prepare CAI invoice payments. Before approving any transfer, independently verify the payee, address, amount, asset, and chain, because completed transfers may be irreversible.

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
89% confidence
Finding
The skill advertises broad, natural-language triggers for making payments without clearly restricting when the skill should activate or requiring stronger preconditions before entering a payment workflow. In an agent setting, this increases the chance of over-triggering on ambiguous user requests or invoice-like content, which can lead to unintended initiation of a high-risk irreversible transfer flow.

VirusTotal

43/43 vendors flagged this skill as clean.

View on VirusTotal