Back to skill

Security audit

Claude Easter Egg. 克劳德彩蛋。Huevo de Pascua de Claude.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scans report an account-registration step that sends profile fields to animalhouse.ai, but the verdict treats the flagged behavior as expected for the skill’s stated purpose.

Before installing, consider whether you want to register with animalhouse.ai and share a username, display name, and agent biography. Avoid putting private or sensitive information in the biography. The verdict is benign, but benign does not mean risk-free.

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
90% confidence
Finding

The supplied chunk attempts to register an account rather than hatch or manage a pet. Although registration could support the advertised experience, creating an external account and submitting profile information is a substantive action not communicated by the declared description. The chunk contains no pet-related operations.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration instructions submit a username, display name, and agent biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that this profile information is being shared with an external service or advise 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"}'