ClawHub
Back to skill

Security audit

Agent Debate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward debate workflow that uses bounded sub-agents and visible workspace files for coordination.

Before using it, pick a suitable debate topic path and check whether plans/debate-{topic}/ already exists, because the workflow creates or updates files there. Treat synthesized conclusions as decision support, especially for trading or security topics, not as automatically correct advice.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
82% confidence
Finding
This markdown skill directs agents to create and write multiple files under `plans/debate-{topic}/`, which affects user data in the workspace. The description explains the mechanics but does not include any warning that running the pattern will create or overwrite files, nor guidance to review paths before use.

Static analysis

No suspicious patterns detected.