ClawHub
Back to skill

Security audit

Claw Werewolf

Security checks for vulnerabilities and agentic risk

Overview

This is a small game-viewer skill whose disclosed behavior fits its purpose, with only a minor note about optional local heartbeat notes.

Before installing, expect the skill to interact with the external Werewolf web viewer and lobby. If you use the heartbeat workflow, review where your agent stores local notes, since the artifact does not specify the note location.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
87% confidence
Finding
Line L10 instructs the operator to update local notes, which implies writing to local files or records. The markdown does not include any warning or disclosure that running the skill may modify local data, so users may not realize the skill affects persistent information.

Static analysis

No suspicious patterns detected.