ClawHub
Back to skill

Security audit

Foresea

Security checks across malware telemetry and agentic risk

Overview

This skill transparently connects forecasting questions to Foresea's external MCP service and does not show hidden, destructive, or credential-seeking behavior.

Install this only if you are comfortable sending forecasting or prediction-market questions, and any context you include in those questions, to Foresea's external service. Treat forecasts as decision support, not financial advice.

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 skill instructs invocation for very broad topics like probability, likelihood, forecasts, prediction markets, and whether a future event will happen. This can cause the agent to route ordinary conversational or analytical questions to a third-party remote MCP service unnecessarily, increasing external data exposure and expanding the trusted execution surface beyond the user's likely expectations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal