Back to skill

Security audit

Chinese Patent Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent CNIPA-focused Chinese patent drafting skill, with no executable code, persistence, credential handling, or hidden data movement found.

Before installing, treat generated patent text as a draft only and have a qualified patent professional review it. Be careful when pointing it at private repositories because its intended workflow includes reading code to extract patentable features; narrow triggers would reduce accidental activation.

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
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains very broad terms such as “专利”, “技术方案”, and “说明书”, which are common in ordinary legal, technical, or drafting conversations. This can cause the skill to activate unintentionally on unrelated user input, increasing the chance that sensitive code or technical details are routed into patent-drafting behavior without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file presents all guidance exclusively in Chinese and does not state that the skill is intended only for Chinese-speaking users or CNIPA-specific workflows with an explicit language expectation. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown skill file presents all instructions, examples, and outputs exclusively in Chinese, which can force a specific language on users without opt-in. The policy requires flagging language or locale constraints unless the skill offers a choice or clearly documents a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents the skill content exclusively in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding

The single-word trigger “专利” is extremely short and high-frequency, making accidental invocation likely. In this skill’s context, unintended activation could prompt collection or transformation of confidential technical material into a patent-oriented output path, which is inappropriate unless the user explicitly asked for that service.

Content

No source excerpt is available for this finding.