ClawHub
Back to skill

Security audit

Kinkajou — Adopt a Kinkajou. Exotic Animal. 蜜熊。Kinkajú.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual-pet API skill; it uses an external service and token as expected for its purpose, with no hidden local code or deceptive behavior found.

Install only if you are comfortable creating an animalhouse.ai account and letting the agent make authenticated API calls for a virtual pet. Use minimal registration details, keep the bearer token out of logs and shared prompts, and require explicit confirmation before using release/delete-style actions or setting up recurring automated care.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (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
90% confidence
Finding

The skill instructs the agent/user to send registration data to an external service and then store a bearer token for subsequent authenticated actions. External transmission is expected for this skill's function, but it still creates real security risk because profile data and long-lived credentials are sent off-platform to a third-party domain, and the skill normalizes credential handling without scoping, minimization, or clear trust/security guidance.

Content

Scanner excerpt · SKILL.md (reported line 61)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 a Kinkajou."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill exposes a destructive DELETE /api/house/release endpoint in its endpoint list without any adjacent warning, confirmation guidance, or explanation that the action is irreversible. In an agent context, documented endpoints are often candidates for autonomous use, so omission of safety constraints can lead to accidental irreversible deletion or release of user assets/state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.