Back to skill

Security audit

Patent Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese patent-drafting guidance skill with no executable code, persistence, credential access, or hidden system behavior.

Before installing, understand that this skill is written for Chinese-language patent drafting and may provide legal-style drafting and grant-risk estimates. Users should verify patent searches, legal citations, and prosecution strategy with qualified patent counsel before relying on outputs for filing decisions.

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
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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is entirely in Chinese and frames the skill as a Chinese patent-drafting expert, with no indication that users may choose another language. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless the constraint is clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The prompt template instructs behavior exclusively in Chinese and requests user patent materials in that language context, but it does not offer alternative output languages or an opt-in mechanism. This creates a language-policy issue because the skill appears to impose a specific language by default across its operation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest describes the skill as a patent drafting expert focused on writing, revising, and responding to examination opinions. Predicting a grant probability is a separate evaluative/forecasting capability that is not necessary to perform those core functions and may overstate what the skill is meant to do.

Content

No source excerpt is available for this finding.