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 rates this skill benign with high confidence: the checks completed and the reported concerns were judged consistent with its stated purpose, though sharing profile details externally merits care.
Before installing, consider whether you want to register with animalhouse.ai and share a username, display name, and biography there. Use non-sensitive profile details. The verdict is benign, not risk-free; the scan covered the reported single Markdown file, and some executable behavior checks were not applicable.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The adoption workflow instructs the agent to submit a username, display name, and free-text biography to animalhouse.ai. Although the destination is visible in the command, the skill provides no privacy warning about sharing these fields externally or guidance against including sensitive user or system information.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# 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"}'