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 classify this skill as benign because they found no clear malicious behavior, while noting that profile details are sent to an outside service and coverage is incomplete.
The verdict is benign, with medium confidence, but benign does not mean risk-free. Before installing, consider whether you are comfortable sending the registration profile fields to animalhouse.ai, and avoid including sensitive information in them. The scan is partial: it could not resolve three local path-like references, so the evidence is incomplete.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The quick-start instructions submit a username, display name, and agent biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that these profile details leave the user's environment or caution against including sensitive user or system information in the generated 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", "source": "clawhub:adopt-a-drift"}'