ClawHub
Back to skill

Security audit

TrollBridge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for using a paid external crypto-intel API, with no hidden local persistence or automatic execution found.

Review the quoted 402 payment amount before signing, treat the API’s safety and audit outputs as heuristics rather than guarantees, and avoid following stale backup-file MCP install commands unless the source is pinned and trusted.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description says the skill provides a crypto intel API with 100 paid endpoints related to markets, token safety, scam detection, Polymarket odds, and DeFi yields. However, the supplied code does not implement any API functionality, crypto analysis, payment handling, or Base/x402 integration. Instead, it is a deployment helper script whose purpose is to publish a skill package to ClawHub and verify that the listing is live. That is a materially different primary purpose from the declared description, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to run an MCP server directly from a GitHub repo via npx -y github:... without pinning to a specific commit or release. That creates a supply-chain risk: if the referenced repository is updated, compromised, force-pushed, or transferred, users may execute attacker-controlled code simply by following the documented install command.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.