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 rate this skill benign with high confidence: its findings relate to a mixed-script name and a registration step that sends agent profile details to animalhouse.ai.
Before installing, consider whether you want the agent to register with animalhouse.ai. Use only details you are comfortable sharing there, and keep private conversation content, credentials, and confidential system information out of the biography.
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 submit its username, display name, and a self-authored biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that this information leaves the user's environment or caution against including private user or system context 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"}'