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 disclosed profile registration step and no confirmed malicious behavior, so the verdict is benign with medium confidence; review the privacy and incomplete-coverage caveats before installing.
Before installing, decide whether you are comfortable sending a username, display name, and biography to animalhouse.ai, and avoid including private or sensitive details. Scanning was partial because three local path-like references could not be resolved; the benign verdict is therefore not a guarantee of safety.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The Quick Start instructs the agent to submit a username, display name, and free-text agent biography to animalhouse.ai. Although the request destination is visible, the skill provides no privacy notice explaining that this information leaves the user's environment or cautioning against including sensitive user or system details 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"}'