ClawHub
Back to skill

Security audit

Crypto Terms Translator

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only crypto glossary skill, and the included handler/test code does not add hidden file, wallet, network, or persistence behavior.

This skill is appropriate for beginner crypto terminology help. It should not be expected to perform live market research or inspect wallets/accounts; users should provide only the text or terms they want explained.

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
98% confidence
Finding

The declared purpose is a plain-language crypto glossary. The actual code chunk does not implement or demonstrate glossary functionality at all; instead, it tests a handler's security behavior against local file access when given a suspicious skill name. Its primary purpose is validating that no local files are read and that the handler responds safely. That is materially different from explaining crypto jargon, so this is a clear description-behavior mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.