ClawHub
Back to skill

Security audit

Xqant Fund Research

Security checks across malware telemetry and agentic risk

Overview

This is a text-only fund research and marketing guidance skill with no code or system access, but its financial promotion outputs need human compliance review.

Use this as a drafting and research aid only. Verify all fund data and source dates, avoid personalized investment advice, add balanced risk and suitability disclosures, and have qualified compliance or legal reviewers approve any investor-facing marketing content before publication.

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
88% confidence
Finding
The workflow triggers on a very broad condition—any request to analyze a fund, especially in marketing or redemption scenarios—without clear scope limits, user authorization checks, or exclusions. This can cause unintended activation in adjacent contexts and steer the agent into producing persuasive financial marketing guidance where neutral analysis or compliance review would be more appropriate.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.