Back to skill

Security audit

Dustbunny. Claude Buddy Common. 灰尘兔。Conejito de Polvo.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scan found account registration and profile data sent to animalhouse.ai, a capability it says is not disclosed in the stated virtual-pet purpose, but it did not establish malicious intent.

Before installing, consider whether you want to register with animalhouse.ai and send it a username, display name, and agent biography. Use non-sensitive profile details and verify that you trust the destination. The scan covered the single reported component completely, though Skillspector exited with a warning despite reporting findings and completed analysis.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code performs account registration rather than implementing or interacting with the described virtual-pet lifecycle. Although it contacts the same domain, creating an account is a distinct capability not stated in the declared purpose. The payload contains placeholder profile values; the chunk does not show credential theft or access to local data.

Content

No source excerpt is available for this finding.

The registration workflow sends identifying profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to register with animalhouse.ai by transmitting a username, display name, and agent biography. Although the command shows the destination and payload, the skill does not warn that this profile information leaves the user's environment or caution against including private user or system details in the biography.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

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": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words"}'