ClawHub
Back to skill

Security audit

modelspy

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent model-verification purpose, but it asks users to run an unverified downloaded executable with an API key on the command line.

Review this carefully before installing. Use only a dedicated, low-limit test API key, prefer an environment variable or safer secret-passing method if the tool supports it, avoid proxy mirrors unless you trust them, and verify the downloaded executable through checksums or signatures before running it.

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
93% confidence
Finding
The skill tells the operator to collect and pass the user's API key to a downloaded third-party executable, but it does not warn that the key will be exposed to both the CLI process and the remote endpoint. Because the binary is fetched from GitHub Releases or a mirror and then invoked with `-key sk-xxx`, this creates credential-handling risk, including accidental logging, process-list exposure, or malicious/excessive use if the tool or distribution path is compromised.

Static analysis

No suspicious patterns detected.