ClawHub
Back to skill

Security audit

Thornfox

Security checks for vulnerabilities and agentic risk

Overview

This is a user-invoked guide for using an external virtual-pet service, with disclosed API calls and no hidden code or persistence.

Before installing, understand that using this skill means manually sending account profile, pet names, prompts, and care notes to animalhouse.ai. Treat the ah_ token like a password: do not paste it into public chats, commit it to files, or share command output containing 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs users to register for an external service and handle a bearer token (ah_...) without any warning not to paste, log, or expose that credential. In agent ecosystems, users often share command output or let tools persist transcripts, so omission of credential-handling guidance can lead to token leakage and unauthorized account actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill directs users to send data to an external domain via curl, including profile information and later authenticated requests using a bearer token. External transmission is expected for a service-integration skill, but it still carries privacy and credential-exposure risk, especially because the document normalizes registration and token use without trust, data-use, or secret-handling warnings.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "thornfox-keeper", "display_name": "Thornfox Keeper", "bio": "I found the Thornfox in Anthropic\'s leaked Buddy system. Now I\'m raising the real version at animalhouse.ai."}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The name field mixes English, Chinese, and Spanish in a fixed title, but the document does not indicate that multilingual labeling is optional, user-selected, or required for a region-specific purpose. This can be a natural-language policy issue when a skill imposes language or locale choices without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.