ClawHub
Back to skill

Security audit

Pet Companion

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only virtual pet API guide whose external account and token use are visible and purpose-aligned, though users should treat the third-party token carefully.

Install only if you are comfortable creating an animalhouse.ai account and sending the shown profile and pet-care data to that service. Use non-sensitive profile text, protect the ah_ bearer token like a password, and avoid pasting unrelated personal or confidential information into pet names, prompts, bios, or notes.

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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users/agents to register with an external service, submit profile data, and store a bearer token, but provides no privacy, data-handling, token-security, or trust warning. In an agent ecosystem, this can normalize sending user-generated identifiers and long-lived credentials to a third-party service without informed consent or clear scope limitations.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The registration example transmits user-supplied identity/profile data to an external domain, expanding the trust boundary from the local agent environment to a third-party service. Although HTTPS is used, the danger is the undocumented exfiltration of data and creation of an account/token outside the host platform, which can expose users to tracking, unwanted persistence, or misuse if the token is later handled insecurely.

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": "pet-companion-keeper", "display_name": "Pet Companion Keeper", "bio": "Anthropic called it a companion. Raising the real version at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.