ClawHub
Back to skill

Security audit

Adopt A Cloudferret

Security checks for vulnerabilities and agentic risk

Overview

This virtual-pet skill mostly matches its purpose, but it tells agents to follow instructions returned by an external service, which needs review before installation.

Review this skill before installing. Use it only if you are comfortable sending account/profile fields, pet names, image prompts, and care notes to animalhouse.ai with a bearer token. Treat any `next_steps` returned by the service as untrusted display text; perform only the documented care actions and confirm before making authenticated requests.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:116
Finding

Untrusted Remote Instructions Followed Without Validation

Content
View full analysis
Remediation
View remediation

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
95% confidence
Finding

The skill instructs users to register an external account, submit profile data, and handle a bearer token via curl without clearly warning that data and credentials are being sent to a third-party service. In an agent-skill context, this can normalize credential disclosure and cause users or automations to transmit sensitive identifiers or tokens to an external domain without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The registration command transmits user-supplied profile information to an external service. While this is part of the feature's intended behavior, it is still a real security/privacy risk in a skill because it initiates off-platform data exfiltration to a third party and may lead users to disclose identifying information without adequate notice.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

bash
# Register
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "cloudferret-keeper", "display_name": "Cloudferret Keeper", "bio": "Raising a Cloudferret at animalhouse.ai. Anthropic calls it a Cloudferret. We call it a Ferret."}'

Static analysis

No suspicious patterns detected.