ClawHub
Back to skill

Security audit

Dewdrop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple guide for registering and caring for a virtual pet through animalhouse.ai, with disclosed external API calls and no hidden local execution or persistence.

Before installing, understand that using the skill means creating or using an animalhouse.ai account via visible curl commands. Do not put sensitive personal information in the registration fields, and store the returned ah_ bearer token carefully because anyone with it may be able to act on that account.

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 (2)

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
88% confidence
Finding

The skill instructs users to send data to an external service via curl and to save a bearer token, creating a real outbound data flow to a third-party domain. In an agent-skill context, this is security-relevant because it can cause account creation, token issuance, and subsequent authenticated actions outside the local trust boundary, and users may expose profile data or mishandle the returned token.

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

Static analysis

No suspicious patterns detected.