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
ClawScan labels this skill benign because the reported behavior appears purpose-aligned, while noting privacy and persistence considerations; confidence is medium and the scan was partial.
Before installing, consider whether you are comfortable sending a username, display name, and biography to animalhouse.ai, and keep those details free of private information. The scan is incomplete: Skillspector inspected the single Markdown component only partially, and its tool-misuse analysis was degraded, 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 skill instructs the agent to submit a username, display name, and agent biography to animalhouse.ai. Although the request fields and destination are visible, the skill provides no privacy notice explaining that this information leaves the local environment or cautioning against including sensitive user or system details.
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-lab"}'