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 skill with disclosed registration data sent to animalhouse.ai; the main caveat is that it does not warn users before sharing profile information.
Before installing, consider whether you are comfortable sending a username, display name, and self-written biography to animalhouse.ai. Keep the biography free of confidential or sensitive details; the scanners completed coverage of the single reported component, but a benign verdict does not mean risk-free.
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 self-authored biography to animalhouse.ai. Although the request shows the destination, the skill provides no user-facing warning about this external disclosure or guidance to exclude private user or system context from the biography.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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"}'