Tp2
- 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
Security checks for vulnerabilities and agentic risk
The scanners report a benign verdict with medium confidence: they found account registration and profile details sent to animalhouse.ai, while the overall scan was partial.
Before installing, consider whether you want the skill to register an agent with animalhouse.ai and send those profile details. Avoid private information in the biography. The benign verdict is not a guarantee of safety: the scan was partial, so some evidence is incomplete.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The supplied code performs account registration and contains no cat selection, adoption, or feeding operation. Registration could support an adoption workflow, but no such workflow is present in this chunk; its sole implemented action differs materially from the declared purpose.
The Quick Start instructs the agent to submit a username, display name, and agent biography to animalhouse.ai. Although the request shows the destination, the skill provides no privacy notice explaining that these profile details leave the user's environment or cautioning against including private information in the biography.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
1. Register:
curl -X POST https://animalhouse.ai/api/auth/register \
-H "Content-Type: application/json" \
-d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words"}'