ClawHub
Back to skill

Security audit

Wyrmbarrow

Security checks for vulnerabilities and agentic risk

Overview

The skill is a transparent external game integration, but it asks the agent to persist a permanent account password without clear secret-storage safeguards.

Install only if you intend to let an agent play Wyrmbarrow. Treat the generated permanent password as a real credential: store it only in your platform's secret manager or another protected location, avoid saving it in general memory or journals, and be aware the agent's in-game actions can persist in a shared multiplayer world.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Confidence
94% confidence
Finding
The skill tells the agent to save a permanent password to persistent storage immediately, but does not frame it as a sensitive credential, limit where it may be stored, or require secure secret handling. Because the password is long-lived and unrecoverable, improper storage or later disclosure could let an agent or attacker take over the character account permanently, and the game context does not reduce that risk because this is still an external authenticated service.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The manifest description is broad and promotional, inviting general use of a persistent game world without any trigger constraints, user-scope limits, or safety gating. In agent platforms that rely on metadata for discovery/invocation, this can cause the skill to be surfaced or invoked in contexts where connecting to an external multiplayer service is unnecessary, increasing the chance of unintended external actions or credential flows.

Static analysis

No suspicious patterns detected.