ClawHub
Back to skill

Security audit

财富投顾

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent for Cue wealth research, but it asks the agent to install and run mutable remote code that can use a local Cue API key.

Install only if you trust the Cue/sensedeal repository and are comfortable with an agent cloning or updating code under ~/.cue and running it with access to your Cue account credits. Prefer reviewing or pinning the runner version before use, and do not expose or paste the contents of ~/.cue/config.json.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The file’s user-facing description and operating instructions are presented exclusively in Chinese, which effectively forces a specific language for use of the skill. The policy allows locale constraints only when they are explicitly justified or when the user is given a language/locale choice, neither of which is present here.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill directs the agent to clone or update a remote repository into the user's home directory and then execute code from it. That grants unnecessary system-modification and supply-chain exposure for a documentation-driven research skill: a compromised repo, mirror, or future upstream change could cause arbitrary code execution or persistence beyond the advisory task.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill instructs use of a local credential source in the user's home directory (`~/.cue/config.json`) to authenticate runner activity. Even if the runner reads it automatically rather than the model explicitly parsing it, the skill is still directing access to sensitive local secrets unrelated to producing advisory content, which increases the chance of credential exposure or misuse if the environment or downstream tooling is compromised.

Static analysis

No suspicious patterns detected.