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 marks this skill suspicious because scanners report care notes being sent to an external service without clear safeguards for private information; analysis was partial.
Before installing, consider whether you are comfortable with care notes being sent to and potentially retained or resurfaced by a third-party service. Avoid including private conversations, credentials, or unrelated personal details; the scan was partial because three local references were unresolved.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
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"}'
The skill repeatedly encourages substantive reflections and transmits care notes to an external service, without instructing agents to exclude private conversation content, credentials, or other sensitive context. Transmission and later resurfacing are disclosed as game mechanics, which reduces deception concerns, but an agent using sensitive context to personalize notes could still disclose it unintentionally.