ClawHub
Back to skill

Security audit

Mortgage Rate Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small weather-briefing prompt package with disclosed packaging hooks and no evidence of hidden network, credential, persistence, or destructive behavior.

Before installing, understand that this package appears to provide a weather-briefing prompt, not a full live weather integration. Use it with a trusted weather data source if factual forecasts matter. The included hooks are ordinary local packaging checks and do not show security-impacting behavior beyond creating build metadata.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The declared description says the skill provides a daily weather briefing, but the supplied code does not fetch, summarize, or otherwise handle weather data. Instead, it performs packaging/setup tasks: creating a build directory, reading metadata from SKILL.md, copying prompt.txt, and writing package-info.json. These are build-time support functions and indicate a primary behavior unrelated to the declared end-user purpose in this code chunk.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description says the skill provides a daily weather briefing, but the supplied code does not fetch, summarize, or present weather information. Instead, it validates the presence and contents of a manifest file (SKILL.md) and checks for specific metadata fields. This is a materially different primary purpose. The code also represents hook/validation behavior, which is unrelated to the declared weather briefing functionality and inconsistent with the empty trigger declaration.

Content

No source excerpt is available for this finding.