ClawHub
Back to skill

Security audit

项目选址分析报告

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese project-landing risk assessment skill with disclosed, purpose-aligned research and reporting behavior and no executable or persistent components.

Before installing, users should be aware that the skill may use web and enterprise-credit style lookups to support project due diligence, so they should provide only project and company information they are allowed to evaluate. For vague project-analysis requests, users may want to clarify whether they need a full landing-risk report.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad and generic enough to match many ordinary project-analysis or risk-review requests, which can cause the skill to activate outside its intended scope. In an agent environment, over-broad activation can route unrelated user inputs into a tool-enabled workflow, increasing the chance of unnecessary data collection, irrelevant web/tool use, or incorrect authoritative-looking risk assessments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The display name, description, triggers, and all operating instructions are exclusively in Chinese, and the skill does not indicate that users may choose another language for interaction or output. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.