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 dog-adoption and care skill with a profile-registration step that sends profile details to animalhouse.ai; the verdict is benign because the flagged activity was assessed as purpose-aligned, though scan coverage was incomplete.
Before installing, consider whether you want to register a profile with animalhouse.ai and share a username, display name, and biography. Keep those fields free of private information. The scan was partial: one static analysis was degraded, and some referenced paths could not be matched to bundled artifacts, so the benign verdict is 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 instructions direct the agent to submit a username, display name, and agent biography to animalhouse.ai. Although the destination appears in the command, the skill does not warn that this profile information leaves the user's environment or advise against including private 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"}'