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 verdict is benign with medium confidence: the scanners found a registration step that sends profile details to an external service, while the flagged findings were judged expected for the skill's purpose; inspection was partial.
Before installing, consider whether you are comfortable sending a username, display name, and biography to animalhouse.ai during registration, and avoid including personal or confidential details unless you intend to share them. The verdict is benign, not risk-free, and confidence is medium; Skillspector's inspection was partial because three local path-like references could not be matched to bundled files.
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 free-text biography to animalhouse.ai without warning about sharing identifying or confidential information. The instruction to store the returned token securely addresses credential handling, not disclosure of the submitted profile data.
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-phoenix"}'