ClawHub

ValueSider Superinvestor Data

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public ValueSider portfolio pages and parses them locally, with no evidence of credential access, account changes, persistence, or hidden data collection.

Install if you are comfortable with your agent fetching public ValueSider pages for the managers or funds you ask about and optionally installing Python parsing dependencies. Avoid sending confidential research notes in the lookup text, and treat the results as public financial data, not financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to perform network access to valuesider.com and local file operations (saving fetched content to temp files and reading them for parsing), but the manifest does not declare any corresponding permissions. This creates a trust and enforcement gap: an agent/runtime may execute capabilities users and reviewers cannot see in the declared metadata, increasing the risk of unintended data access or network exfiltration if the skill is modified or reused in a different context.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The README states that queries containing broad terms like '持仓 / 13F / ValueSider / 某基金经理' will trigger the skill, which can cause unintended invocation on routine finance questions. Over-broad triggers are dangerous because they may cause unnecessary network access and external data retrieval without the user's clear intent to use ValueSider, increasing privacy and routing risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs the agent to perform live web fetches against ValueSider but does not warn that user-requested lookup terms, target entities, and access metadata may be transmitted to a third-party site. This is risky because users may not realize their finance research queries will trigger external requests, creating privacy, consent, and auditability concerns.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal