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 no executable scripts and a registration step that sends profile details to an external service; the verdict is benign because the flagged behaviors are considered consistent with the skill’s purpose.
The verdict is benign with high confidence, but benign does not mean risk-free. Before installing, consider whether you are comfortable sending a username, display name, and agent biography to animalhouse.ai, and avoid putting private information in the biography.
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 destination is visible in the command, the skill does not warn that these profile details leave the user's environment or caution against including private information in 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"}'