ClawHub
Back to skill

Security audit

观势深度洞察引擎

Security checks for vulnerabilities and agentic risk

Overview

This skill is an analysis-methodology helper that asks an agent to critique and deepen strategy conclusions, with no code execution, persistence, credential access, or hidden data flow.

Installers should expect this skill to make answers longer and more adversarial when deeper review is requested. If that is not desired, narrow activation to explicit DeepInsight or Chief-review contexts before use.

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
94% confidence
Finding

The trigger conditions include very common user phrases such as “深入分析”, “再想想”, and “还有什么没考虑到的”, which can cause the skill to activate from ordinary conversational language rather than explicit user intent. This creates scope ambiguity and may lead to unintended invocation, unnecessary processing, or interference with other skills in the pipeline, especially because this skill is designed to insert an additional adversarial review stage into downstream analysis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.