Back to skill

Security audit

Patent Writer Cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese patent and software copyright drafting assistant, with no evidence of hidden execution, persistence, credential use, or data exfiltration.

Before using it, avoid sharing portal passwords, unnecessary identity document images, secrets, API keys, or unrelated proprietary code. Provide only the technical and filing details needed for the draft, and redact sensitive identifiers where possible.

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
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description lists broad activation terms such as “专利”, “发明点”, and “权利要求”, which can appear in ordinary discussion without the user intending to invoke this specific skill. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly solicits sensitive identity and application materials, including personal/enterprise identification documents, account-related information, screenshots, and detailed technical materials, but provides no privacy notice, minimization guidance, retention limits, or safer handling instructions. In this context, the skill is designed to collect exactly the kinds of information that can enable privacy harm, credential exposure, and IP leakage if mishandled, making the omission materially risky.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire template prescribes Chinese headings, examples, and drafting conventions, which effectively requires a specific language/locale for use. Under the policy criteria, a skill should not force a language without offering user choice or clearly documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file consistently prescribes Chinese-language patent and copyright application assistance and presents the skill as a Chinese-only workflow, but it does not explicitly offer the user a language option. Although the content is China-specific, the policy concern is that the language/locale constraint is not clearly framed as an opt-in or documented limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written in Chinese and provides no indication that users may choose another language or that the language restriction is an explicit, documented requirement of the skill. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.