ClawHub
Back to skill

Security audit

MeatLoop

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for sending user-selected questions or images to a human reviewer by email, with privacy cautions but no local code execution or hidden persistence.

Install only if you are comfortable sending selected questions, screenshots, or images to an external human operator by email. Do not submit secrets, credentials, regulated data, private documents, or confidential business information; sanitize screenshots before use.

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
95% confidence
Finding
This skill explicitly routes user questions and attachments to a third-party human operator via email, and only later states 'Do not submit confidential information' and describes public verification logging. That creates a real privacy and data-handling risk because agents may follow the submission instructions before seeing a prominent warning, leading to unintended disclosure of sensitive screenshots, emails, or documents to a human reviewer and associated external services.

Static analysis

No suspicious patterns detected.