ClawHub
Back to skill

Security audit

Research XCorbit

Security checks for vulnerabilities and agentic risk

Overview

This is a market-research prompt skill with broad but disclosed research-report behavior and no executable, persistent, credential, or destructive capabilities.

Installers should expect this skill to produce detailed, research-heavy product strategy reports and to prefer the '五看三定' framework by default. Users who only want quick brainstorming, copywriting, or implementation help may need to avoid invoking it or ask for a different format explicitly.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broad enough to match generic product, strategy, market, and opportunity questions, which can cause the agent to invoke this skill outside its intended niche. Over-broad routing can override more appropriate domain-specific skills or baseline reasoning, leading to incorrect tool selection, unnecessary external research behavior, and reduced user control over how requests are handled.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The applicable-scenario section lists many positive triggers but almost no boundary conditions or negative examples, so ordinary product questions may be captured too aggressively. In an agent setting, this can create prompt-scope escalation where the skill takes over conversations it should not, increasing the chance of irrelevant instructions, unnecessary web-style research steps, or conflicts with user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description states that the skill '强制纳入' Huawei-style '五看三定' strategic analysis in outputs. This imposes a specific organizational or cultural framework by default rather than offering it as an option or asking the user whether they want that format.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.