ClawHub
Back to skill

Security audit

Debate Learning Workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed debate-note workflow that writes expected local output files but shows no hidden code execution, credential use, network payloads, or destructive behavior.

Before installing, be aware that using this skill will generate debate files on your Desktop and append lessons to a Desktop notes file. Choose a different output location or ask the agent to confirm file writes first if you do not want those files created there.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to create and append to files under the user's Desktop and home directory without any warning, confirmation step, or discussion of side effects. Even though the paths are not inherently sensitive, silent file creation/modification can surprise users, overwrite existing notes, expose private content in predictable locations, or violate least-surprise expectations for agent behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.