ClawHub
Back to skill

Security audit

Portfolio Analytics

Security checks across malware telemetry and agentic risk

Overview

The skill appears to provide advisory portfolio risk analysis, with no evidence of malware, destructive actions, credential theft, or hidden persistence.

Install only if you are comfortable sharing portfolio details with the agent environment. Verify holdings and prices yourself, do not treat the output as trading advice, and prefer explicit invocation for financial decisions.

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
92% confidence
Finding
Implicit invocation allows the skill to be triggered automatically without explicit user intent or tight guard conditions. Because this skill produces portfolio risk analytics that may influence trading, auto-invocation can inject unsolicited financial context into decision flows, increasing the chance of inappropriate reliance, mis-scoped analysis, or use on incomplete holdings data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.