ClawHub
Back to skill

Security audit

PathClaw 病理助手

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently uploads user-selected pathology slide files to the PathClaw service for AI-assisted analysis, with privacy considerations users should review before use.

Before installing, confirm you are allowed to send the selected .svs pathology slide to 华银康集团 PathClaw and that any patient data handling, consent, retention, and compliance requirements are satisfied. Non-Chinese readers should have the prompts reviewed or translated before relying on the workflow.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill directs uploading .svs pathology slide files to a third-party PathClaw service, but does not require an explicit user consent step or warning that sensitive medical data will leave the local/system boundary. Pathology images can contain highly sensitive health information, so silent transmission to an external service creates material privacy, compliance, and data-governance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill description and all prescribed user-facing prompts are fixed in Chinese, with no option for the user to choose another language. The policy only allows locale constraints when the skill offers choice or clearly documents and justifies the restriction as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.