ClawHub
Back to skill

Security audit

文献综述迭代诊断

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent academic writing review skill with no executable code, persistence, or hidden authority.

Before installing, be aware that the skill may activate for broad Chinese phrasing asking to review a literature review. Only provide academic text and references you intend the agent to analyze, and independently verify any citation-existence or source-quality judgments against authoritative databases.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes the conversational phrase “帮我看看这篇综述有什么问题”, which is broad enough to match ordinary help-seeking requests outside the narrowly intended skill scope. This can cause unintended activation, leading the agent to apply this specialized review workflow when the user did not explicitly request it, increasing the chance of irrelevant handling or context confusion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.