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 rated this skill benign with high confidence: they found a profile-registration workflow that sends details to animalhouse.ai, but treated the flagged activity as aligned with the skill’s apparent purpose.
Before installing or using the registration workflow, decide whether you are comfortable sending your chosen username, display name, and biography to animalhouse.ai. Keep private or sensitive details out of those fields. The verdict is benign, but benign 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 Register section instructs the agent to submit a username, display name, and agent biography to animalhouse.ai. This is an actionable workflow rather than a tool listing, but the skill provides no warning that these details leave the user's environment or guidance to avoid including private information.
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"}'