ClawHub
Back to skill

Security audit

Crypto News Noise Filter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow prompt-only aid for critically reading crypto news, with no evidence of hidden access or side effects.

Install only if you want a prompt-based framework for evaluating crypto news headlines. It should not be treated as investment advice or as a live news checker, because it relies on user-provided text and does not fetch current market or regulatory data itself.

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 (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared purpose is a prompt-only crypto news critical-reading aid. The actual code chunk does not implement or demonstrate that functionality. Instead, it tests security behavior: ensuring the handler resists local file access when given a path-like skill name and returns a benign response. That is a materially different primary purpose from analyzing crypto headlines, so this is a mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.