ClawHub
Back to skill

Security audit

ym-doc-version-diff

Security checks for vulnerabilities and agentic risk

Overview

This is a document comparison skill that stays within user-provided content and does not add code execution, network upload, persistence, or hidden authority.

Installers should expect this skill to help compare two provided document versions. Be aware that broad Chinese trigger phrases may invoke it for some general comparison requests, so confirm that you are actually comparing document versions before relying on its output.

A.I.G

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

SkillSpector

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
Confidence
91% confidence
Finding
The trigger phrase "改了哪里" is broad enough to match many casual requests outside the intended document-version-diff context. This can cause the skill to activate unexpectedly, leading to incorrect routing of user requests and unintended handling of content that is not actually a two-version document comparison task.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger "两版区别" is ambiguous because it does not explicitly constrain the subject to documents, contracts, or text versions. In practice, this can over-match unrelated conversations about differences between two things, causing accidental invocation and reducing reliability of agent behavior.

Static analysis

No suspicious patterns detected.