ClawHub
Back to skill

Security audit

TrustGrade Crypto Trust

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto trust-checking and crypto security news integration with no bundled executable code or persistence, though it relies on an external MCP package at runtime.

Before installing, understand that the skill routes crypto trust checks and crypto security news queries through TrustGrade's MCP server and API. Use it as one input for crypto safety decisions, not as investment advice or a substitute for independent verification, especially because the reviewed artifact does not include the npm server implementation 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description includes a broad trigger for 'recent-incident questions,' which can cause the skill to activate for loosely related security or incident queries beyond its core trust-scoring purpose. Over-broad invocation increases the chance the agent will inappropriately route sensitive decision-making or incident-response context through this skill, potentially amplifying incorrect, stale, or externally sourced security claims.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.