ClawHub
Back to skill

Security audit

One Man Conglomerate

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed multi-agent workflow, but it also directs automatic cleanup, archiving, and knowledge-base updates without clear limits or confirmation.

Install only if you are comfortable with an agent coordinating multiple sub-agents and potentially changing project files or persistent knowledge during closeout. Before using the cleanup commands, ask the agent to show exactly what it will archive, delete, or write to memory, and require explicit confirmation before it acts.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes automatic cleanup of temporary files, project archiving, and memory/knowledge-base updates, but does not warn the user that these are data-affecting operations or explain what will be modified. In a multi-agent orchestration context, implicit cleanup behavior is more dangerous because multiple agents may amplify the chance of acting on the wrong files or persisting unintended state changes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrase "整理一下 这个项目" is broad, conversational, and likely to appear in normal user dialogue without a clear intent to authorize cleanup actions. In a skill that advertises automatic file cleanup and archiving, this creates a risk of unintended destructive or data-affecting operations being initiated from ambiguous natural language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.