Fund Signal Monitor

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.1.0

Overview

This is a disclosed, documentation-only fund monitoring skill; users should still verify the separate fund-analyzer-pro implementation before enabling alerts.

Before installing, treat alerts as informational only and verify fund events against official disclosures. Review fund-analyzer-pro's signal_checker.py separately, confirm what credentials and push destinations it uses, where watchlists are stored, whether encryption is actually implemented, and how to disable or remove scheduled monitoring.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The assessment contains internally contradictory statements about whether a disclaimer exists versus whether a disclaimer template is still missing. In a security and compliance review document, this inconsistency can mislead reviewers into believing a required user warning is already implemented, which may allow an inadequately safeguarded skill to be approved or published.

Intent-Code Divergence

Medium

• Confidence: 98% confidence
• Finding: The document states that the user monitoring list is encrypted while also marking encryption as '待实现' (to be implemented), which is a direct contradiction about protection of potentially sensitive user preference data. This can create a false assurance that data-at-rest protections exist when they do not, leading to weaker handling of user data and approval of an unsafe implementation.

Intent-Code Divergence

Low

• Confidence: 90% confidence
• Finding: The version-management section claims a CHANGELOG exists, but the improvement section later says CHANGELOG.md still needs to be added. While lower severity than the security contradictions, this still undermines trust in the accuracy of the assessment and suggests the document may have been produced without adequate verification of evidence.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The assessment explicitly notes that the skill description lacks a required disclaimer or warning, which is important in a fund-monitoring context where outputs could influence financial decisions. Without a clear disclaimer, users may over-trust automated monitoring signals as advice, increasing legal, compliance, and user-harm risk.

VirusTotal

65/65 vendors flagged this skill as clean.