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 skill is rated benign with high confidence; scanners found no executable scripts and identified a registration step that sends profile details to animalhouse.ai, treated as purpose-aligned behavior with a privacy note.
Before installing or using the skill, consider whether you want to register with animalhouse.ai. Only provide profile details you are comfortable sending to that service, and avoid private conversation content, credentials, or system details.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The registration step instructs the agent to send a username, display name, and free-text agent biography to animalhouse.ai. Although the command shows the destination, the skill provides no warning that this profile information leaves the local environment or guidance to exclude private user or system details 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"}'