ClawHub
Back to skill

Security audit

Foresea

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently installs and uses a public forecasting MCP service, with no local code execution, credential use, hidden persistence, or destructive behavior found.

Before installing, understand that forecasting questions may be sent to Foresea's remote MCP service. Avoid using it for private or sensitive scenarios unless you are comfortable sharing those query details with that service.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation guidance is broad enough to match many ordinary questions about probability, likelihood, or future events, which can cause the agent to invoke a third-party remote MCP service more often than users may expect. That increases unnecessary external data exposure and dependency on an untrusted remote tool, especially when the request could be answered locally or does not require market-related analysis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.