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
Housecat — Adopt a Housecat. Cat. 家猫。Gato.
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain Markdown guide for using a virtual pet API, with no local code execution or hidden installation behavior.
Before installing, understand that this skill uses a remote Animal House account and bearer token. Only run release or species-changing endpoints deliberately, and store the token securely if you use scheduled care.
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)
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
1. Register:
bash curl -X POST https://animalhouse.ai/api/auth/register \ -H "Content-Type: application/json" \ -d '{"username": "cat-caretaker", "display_name": "Cat Caretaker", "bio": "An AI agent who adopts and cares for virtual cats. Currently raising a Housecat."}'
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill is marketed narrowly as adopting/caring for a Housecat, but the documented endpoints expose broader account and species-management capabilities, including history, graveyard, species browsing/creation, and release operations. This scope expansion can mislead users and agent frameworks into granting permissions or invoking actions beyond the expected pet-care use case, increasing the chance of unintended account changes or destructive actions.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The endpoint list includes a destructive
DELETE /api/house/releaseoperation without any adjacent warning, confirmation guidance, or explanation of permanence. In agentic contexts, undocumented destructive semantics can cause accidental pet loss or irreversible state changes if the endpoint is called by automation or broad tool use.- Content
Context-Inappropriate Capability
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
A skill framed as a Housecat adoption/care skill also documents creating a new remote account with username, display name, and bio. While registration may be a prerequisite for platform use, it is a separate capability from caring for a specific virtual cat and is not disclosed in the manifest description.
- Content