ClawHub
Back to skill

Security audit

公募基金全维尽调

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Cue-based fund due-diligence workflow that sends user fund research queries to an external API and stores normal Cue credentials/session state locally.

Before installing, confirm you are comfortable sending fund research prompts to Cue/cuecue.cn and related data providers, and avoid putting private account numbers, credentials, or nonpublic client information in queries. Protect ~/.cue/config.json as a secret-bearing file and be aware that Cue session state may remain under ~/.cue/session/task for resumable jobs.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly routes user queries to Cue's external API and instructs users to store an API key in ~/.cue/config.json, but it does not present a clear upfront warning about third-party transmission and local secret storage. This can mislead users into sending sensitive fund research prompts or credentials without informed consent, increasing privacy and secret-handling risk.

Static analysis

No suspicious patterns detected.