ClawHub
Back to skill

Security audit

external-tech-acquisition

Security checks for vulnerabilities and agentic risk

Overview

This workflow skill is purpose-aligned and has no executable code or hidden persistence, but users should treat its external MCP use carefully when handling confidential business materials.

Install only in an environment approved for Patsnap/Zhihuiya MCP use. Before uploading internal templates, budgets, due-diligence notes, or proprietary technology descriptions, confirm your organization's confidentiality and data-governance rules and redact sensitive details where possible.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger conditions are broad and match common enterprise phrases such as '成果转化' and '技术引进' without boundary checks, making accidental activation likely. In this skill, unintended activation can route sensitive strategic discussions and proprietary technology descriptions into external MCP-backed processing flows, increasing the chance of unnecessary data exposure and confusing users about when external services are being used.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill invites users to upload internal project templates and generate decision materials, but does not clearly warn that these materials may contain confidential enterprise, legal, strategic, or IP-sensitive information that could be transmitted to external MCP services. In the context of a央企 technology acquisition workflow, this omission is especially risky because the documents may include non-public investment plans, due-diligence records, and approval materials whose external processing could create confidentiality, compliance, or data-governance violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language instructions, examples, and workflow descriptions are all presented in Chinese, which may effectively force a specific language experience. There is no statement that the user may choose another language or that Chinese is required for a justified region-specific reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.