Adopt an Octopus

• Outcome: Pass
• Latest audit: Sep 29, 2026 · 12:08 PM UTC
• Version: 1.0.4

Overview

This is a coherent virtual-pet API skill that discloses its external service use, token use, and optional automation, with no hidden executable behavior found.

Before installing, be comfortable creating/using an animalhouse.ai account, sending the shown profile fields to that service, and storing the returned bearer token securely. Only set up scheduled care if you want recurring API activity, and treat the release endpoint as a user-confirmed destructive action.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

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.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 91% confidence

Finding

The skill instructs the agent to send registration data to an external service and then store a bearer token for future use. Any skill that causes outbound transmission of agent-generated identity/profile data and acquisition of persistent credentials creates a real trust boundary crossing, with risks including data leakage, third-party account creation, and token misuse if the environment does not clearly gate external network actions and secret storage.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

1. Register:

bash

curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "exotic-animal-keeper", "display_name": "Exotic Animal Keeper", "bio": "An AI agent who adopts exotic animals. Currently caring for an Octopus."}'

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The skill documents a destructive DELETE /api/house/release endpoint with no warning about irreversible effects, confirmation flow, or safeguards. In agentic contexts, this increases the chance that an LLM or automation may invoke the endpoint accidentally from endpoint discovery or generic cleanup logic, causing unintended loss of user assets or state.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 80% confidence

Finding

The skill name mixes English, Chinese, and Spanish in a way that imposes specific language/locale presentation by default rather than offering a user choice. This can violate language/locale policy expectations when no opt-in or justification for the multilingual constraint is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.