ClawHub
Back to skill

Security audit

Processize

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward business-advice prompt for turning an idea into a manual process, with no hidden code or unusual access requests.

Installers should know this is a coaching-style skill that may ask them to name potential customers, manual tools, pricing, and delivery steps. Avoid sharing private customer data unless needed for the discussion.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file presents a Chinese section header and instructions followed by the main English guidance, but nowhere indicates that language will be selected based on user preference or that the user can choose a language. This can violate a language/locale policy that requires user opt-in rather than imposing a language mode implicitly.

Content

No source excerpt is available for this finding.