ClawHub
Back to skill

Security audit

Debate con agent for you

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed debate-opposition prompt with no code execution, persistence, credential access, or hidden data handling.

Install this only if you want a deliberately critical debate partner. It may give blunt opposition-style feedback when invoked, so avoid using it for emotional support or situations where collaborative planning is more appropriate.

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 activation criteria are broad enough to trigger on many normal discussions involving plans, viewpoints, or requests for review, not just explicit adversarial debate tasks. That can cause unintended invocation and steer the assistant into unnecessarily oppositional behavior, degrading reliability and potentially producing harmful or disruptive responses in sensitive contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.