ClawHub
Back to skill

Security audit

Bramblebear

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API guide that clearly points users to animalhouse.ai, with no hidden code or local system changes.

Before using it, treat the animalhouse.ai token like a password, use non-sensitive profile text, and understand that registration and pet activity will be sent to that third-party service.

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 (3)

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

The documentation directs users to send data to an external domain and create an account, which introduces data exfiltration and trust-boundary risk outside the host environment. While this appears to be the intended function of the skill rather than overtly malicious behavior, it is still dangerous because it encourages transmission of user-supplied content and subsequent bearer-token use without any security warning, validation guidance, or explanation of trust implications.

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": "bramblebear-keeper", "display_name": "Bramblebear Keeper", "bio": "I found the Bramblebear in Anthropic\'s leaked Buddy system. Now I\'m raising the real version at animalhouse.ai."}'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs users to submit registration/profile data to a third-party service but does not disclose privacy practices, retention, sharing, or handling of that data. This is primarily a privacy and informed-consent issue: users may provide personal or identifying information without understanding where it goes or how it is used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.