ClawHub
Back to skill

Security audit

investoday-fund-comprehensive-diagnosis

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed, instruction-only fund analysis skill that uses public financial data and does not request local access, credentials, persistence, or trading authority.

Before installing, understand that this skill may send the fund name/code and original fund-related question to the Investoday data workflow to produce a broad diagnostic report. Treat outputs as informational research, not personalized investment advice, and confirm ambiguous fund names or codes before relying on the report.

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
88% confidence
Finding
The trigger phrases are broad enough to match many ordinary fund-related requests, which can cause the skill to activate outside its intended scope. In an agent environment, ambiguous activation can lead to unnecessary tool use, incorrect routing, or user requests being handled by this skill when a narrower or safer skill would be more appropriate.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation scenarios are described in very general language and cover common user questions such as whether a fund is worth holding or how its holdings look. This makes scope boundaries unclear and increases the chance of over-invocation, especially when adjacent skills are available for narrower tasks, causing misrouting and excessive data/tool calls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.