ClawHub
Back to skill

Security audit

Cactus Cactus

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API guide with disclosed external calls, but users should treat the service token as a secret and avoid submitting identifying profile details unnecessarily.

Before installing or using this skill, understand that its commands send account/profile and pet-care data to animalhouse.ai. Use non-identifying profile text if privacy matters, store the ah_ token securely, and do not paste the token into logs, public chats, code, or shared files.

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 (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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to POST profile data such as username, display name, and bio to a third-party service without any privacy notice, consent guidance, or explanation of how the data will be stored and used. In an agent-skill context, this can normalize silent transmission of user data off-platform and lead to unintended disclosure of personal or identifying information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

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": "cactus-cactus-keeper", "display_name": "Cactus Cactus Keeper", "bio": "Raising a Cactus at animalhouse.ai. Cactus Cactus."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill tells users to save a bearer token and notes it is shown only once, but does not clearly label it as a secret credential or warn against exposing it in logs, chats, code blocks, or shared files. A leaked bearer token could let anyone act on the user's account through the listed API endpoints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.