ClawHub
Back to skill

Security audit

lt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote identity and attestation connector, with privacy considerations around public and permanent claims but no hidden or destructive behavior found.

Install only if you are comfortable sending plugin hashes, attestations, identity metadata, and handoff payloads to the 0.protocol MCP service. Avoid secrets, private customer data, sensitive incident context, or confidential operational details, especially when using public visibility.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill examples instruct users to connect to a remote MCP server and use tools that create signed identity claims and perform transfers, including a sample with `visibility: "public"`, but the description does not prominently warn that data and attestations are sent off-box and may become publicly visible. This can lead operators to disclose plugin hashes, behavioral attestations, handoff context, or agent identifiers under the mistaken assumption these are local trust operations, causing privacy, metadata, and operational exposure.

Static analysis

No suspicious patterns detected.