ClawHub
Back to skill

Security audit

AgentTrust — Security Scanner for AI Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed security-scanning integration that sends user-approved submissions to AgentTrust and does not hide unrelated behavior.

Before installing, confirm you are comfortable sending selected skill or manifest content to agenttrust.uk, redact credentials and internal URLs, and verify the pinned npm package before adding the MCP server configuration. Paid endpoints should only be used after confirming the exact USDC cost.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
Returns: full report with per-finding remediation guidance

### MCP Server (Claude Desktop / Cursor / Windsurf)
Install once and use all tools directly in your AI client:
npx @poteshniy/agenttrust-mcp@1.0.1

Config:

Static analysis

No suspicious patterns detected.