Security audit

Claude Companion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple documented guide for using an external virtual-pet API, with visible network calls and token use but no hidden execution or local persistence.

Install only if you intend to use animalhouse.ai. Treat the returned ah_ token like a password, avoid putting sensitive personal details in username, bio, image prompts, or care notes, and review the service's privacy practices separately because the skill itself does not explain retention or sharing.

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: 86% confidence
Finding: The skill directs users to send registration data to an external service via curl, which is an external transmission of user-supplied data to a third party. While this appears to be the intended function of the skill rather than overtly malicious behavior, the markdown does not disclose privacy expectations, data handling, or trust implications, making the transmission riskier in an agent context.
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": "claude-companion-keeper", "display_name": "Claude Companion Keeper", "bio": "Every article calls it a companion. Raising the real version at animalhouse.ai."}'

Missing User Warnings