Back to skill

Security audit

Patent Writing Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown patent-drafting helper with no executable code, persistence, credential handling, or hidden behavior found.

Use this skill when you want Chinese-language patent drafting, patent-document review, office-action response, or novelty-search support. For non-Chinese jurisdictions or formal legal filing decisions, confirm the target jurisdiction and have a qualified patent professional review the output before relying on it.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and templates strongly enforce Chinese-language operation and China-specific patent framing without asking for the user's preferred language or jurisdiction first. This can mis-handle international matters, produce unusable output for non-Chinese users, and create compliance or accuracy risks when the user intended another language or patent regime.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger text is extremely broad, covering nearly any patent-related activity without defining boundaries, prerequisites, or exclusions. In an agent environment, this can cause over-activation and unintended capture of general legal, technical, or search tasks, increasing the chance that the skill overrides more appropriate instructions or handles sensitive requests without sufficient scope checks.

Content

No source excerpt is available for this finding.