ClawHub
Back to skill

Security audit

Marketplace

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketplace advice guide with no executable code, persistence, credential handling, or hidden behavior.

Install is reasonable for advisory marketplace help. Treat its tax, legal, fee, and platform-policy content as a checklist and verify current rules with official sources before acting; keep account actions, transactions, listings, and messages under explicit user control.

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · compliance.md (reported line 25)May include surrounding context.

md
**Universal violations:**
- Review manipulation (fake reviews, incentivized without disclosure)
- Multiple accounts without approval
- Off-platform transaction solicitation
- Shill bidding on your own items

Static analysis

No suspicious patterns detected.