ClawHub
Back to skill

Security audit

Evez Debate Framework

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a local multi-agent debate helper and does not show hidden network access, credential use, persistence, or destructive behavior.

This appears safe to install for structured debate and adversarial reasoning workflows. Be aware that its trigger description is broad, so it may be selected for general multi-agent or output-quality tasks even when a lighter approach would be enough.

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
89% confidence
Finding

The description says to use the skill for broad situations like 'building multi-agent systems' or 'improving LLM output quality through debate' without defining specific trigger phrases, constraints, or exclusion conditions. In a markdown skill file, this can create ambiguous invocation criteria and increase the chance of unintended activation for many ordinary AI-assistance tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.