ClawHub
Back to skill

Security audit

合同风险自检台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language contract risk review skill with no executable code, persistence, credential access, or hidden data handling.

Before installing, users should understand that contract text can contain sensitive personal or business information and should share only what is necessary. Treat the output as a risk checklist and wording aid, not formal legal advice, especially for high-value, disputed, or regulated matters.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are generic contract-help requests such as '帮我看看合同' and '合同风险', which can match broad everyday user intents and cause the skill to activate in situations where the user did not explicitly request this specific workflow. Overbroad activation increases the chance of unintended interception, privacy exposure of pasted contract text, and routing users into a legal-risk analysis flow without clear consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing name, description, usage instructions, and examples are presented only in Chinese, and the document does not state that the skill is region-specific or provide a user language/locale option. This can amount to a language policy issue if the organization expects skills not to force a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.