Back to skill

Security audit

知识产权自检台

Security checks for vulnerabilities and agentic risk

Overview

This is a benign intellectual-property self-check skill that provides checklist-style guidance without requesting credentials, file access, network access, or persistent changes.

Installers should treat this as a general self-check aid, not legal advice. Avoid sharing unnecessary personal or confidential details, verify licenses and current legal requirements from authoritative sources, and consult an IP lawyer for disputes, lawsuits, or high-value commercial 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
  • 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
89% confidence
Finding

Several trigger keywords are generic high-frequency terms such as '商标', '开源协议', and '图片版权', which may appear in many normal conversations unrelated to invoking this specific skill. Overbroad keyword matching can cause accidental activation, leading to incorrect routing, user confusion, and legal-risk advice being surfaced out of context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language trigger examples are broad conversational phrases that can overlap with ordinary user requests, increasing the chance that this skill activates when the user did not explicitly intend to invoke it. Misrouting to a legal-compliance skill can produce irrelevant or overconfident guidance in contexts where the user expected general advice, which is especially sensitive given the legal subject matter.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.