ClawHub
Back to skill

Security audit

Cue Credit Diligence

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Cue-based credit diligence research workflow that uses public data and requires confirmation before spending credits.

Install this only if you intend to use Cue for credit diligence or related public-data research. Expect it to access Cue services, use your local Cue credentials, and potentially clone/update the Cue runner; approve the research run only when you are comfortable spending credits on the named subject.

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
75% confidence
Finding
The trigger phrases are broad enough that the skill could activate for loosely related requests, causing the agent to enter a high-impact credit-diligence workflow unexpectedly. In this skill, activation can lead to external network access, repository cloning, and a credit-consuming research run, so ambiguous triggering increases the chance of unintended actions and cost-incurring behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal