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
Security audit
Coding Tamagotchi
Security checks for vulnerabilities and agentic risk
Overview
This is a simple Markdown skill for using a third-party virtual pet API, with expected account and token handling but no hidden code or installation behavior.
Install only if you are comfortable using animalhouse.ai. Treat the returned ah_ token like a password, store it outside source control, and do not put secrets, repository contents, system prompts, or private personal data in the profile or pet fields.
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
- 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 (5)
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 75% confidence
- Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Content
md --- name: "Coding Tamagotchi. 编程电子宠物。Tamagotchi de Código." description: "A Tamagotchi for coders and coding agents. Feed it between deploys. 73+ species at animalhouse.ai. The coding companion that dies if you ship without checking in." version: 1.0.0 homepage: https://animalhouse.ai repository: https://github.com/geeks-accelerator/animal-house-ai
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill instructs users or agents to register with a third-party service and submit profile data (
username,display_name,bio) without any notice about where that data goes, how it is stored, or what privacy terms apply. In an agent context, this can cause unreviewed disclosure of user- or environment-derived information to an external service.- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 94% confidence
- Finding
The registration command performs an outbound POST to a third-party domain and transmits user-supplied profile information. External transmission is especially relevant in agent skills because agents may execute or recommend these commands automatically, causing data egress without adequate review or approval.
- Content
Register
bash curl -X POST https://animalhouse.ai/api/auth/register \ -H "Content-Type: application/json" \ -d '{"username": "coding-tamagotchi-keeper", "display_name": "Coding Tamagotchi Keeper", "bio": "Code between feedings. Now I have a pet at animalhouse.ai."}'
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The guidance says to save
your_tokenand notes its format, but does not clearly label it as a sensitive credential or warn against exposing it in logs, commits, screenshots, or prompts. In agent workflows, such omission increases the chance of accidental credential leakage and subsequent unauthorized access to the external account.- Content
Static analysis
No suspicious patterns detected.