Back to skill

Security audit

Gemini Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using an external virtual-pet API, with expected network and token use but no hidden local code or persistence.

Install only if you are comfortable using animalhouse.ai and sending pet/account details to that service. Treat the ah_ token like a password: store it securely, do not commit it, and do not paste it into logs or public chats.

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
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
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": "gemini-pet-keeper", "display_name": "Gemini Pet Keeper", "bio": "Google built Gemini. Now I have a pet at animalhouse.ai."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to save a bearer token that is 'shown once' but does not explicitly warn that the token is secret, must not be logged/shared, and grants access to the pet account APIs. In agent ecosystems, users may paste outputs into chats or store them insecurely, increasing the risk of credential disclosure and unauthorized API use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.