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 skill with a registration step that sends profile details to animalhouse.ai; the verdict is benign because the flagged behavior is considered purpose-aligned, though privacy and partial-coverage notes remain.
Before installing, consider whether you are comfortable registering with animalhouse.ai and sharing a username, display name, and biography. Use only profile details you are comfortable sending externally. The overall verdict is benign, but confidence is medium and inspection was partial because three local references could not be resolved.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The registration workflow instructs the agent to send a username, display name, and agent biography to animalhouse.ai. Although the request payload is visible, the skill provides no privacy warning explaining that these profile details will leave the user's environment and be submitted to an external service.
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"}'