Security audit

Crypto Scam Red Flags

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only crypto scam screening skill with no evidence of hidden file access, persistence, or external execution.

Installers should understand that this skill can help reason about pasted crypto offers or messages, but it cannot independently inspect links, smart contracts, wallets, domains, or accounts in real time.

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: 94% confidence
Finding: The declared purpose is a scam-screening assistant that analyzes suspicious messages or offers. The provided code chunk does not implement or exercise scam-analysis behavior at all. Instead, it tests that the handler resists a path-like skill name and does not read local files, which is a security/sandboxing behavior. That is a materially different primary purpose from scam screening, so this is a mismatch.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.