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
This is a small markdown-only virtual pet skill that uses disclosed animalhouse.ai API calls and does not include hidden code, local access, or persistence.
Install only if you are comfortable creating an animalhouse.ai account and sending pet/profile/care data to that service. Treat the ah_ token as a password: keep it out of chat logs, screenshots, shell history, and files you might share.
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.
curl -X POST https://animalhouse.ai/api/auth/register \
-H "Content-Type: application/json" \
-d '{"username": "snail-snail-keeper", "display_name": "Snail Snail Keeper", "bio": "Raising a Snail at animalhouse.ai. Snail Snail."}'
The documentation repeatedly instructs users to place a bearer token into curl commands but gives only minimal handling guidance ('Shown once') and does not clearly warn that the token is a secret that must not be logged, shared, committed, or exposed in shell history. This can lead to accidental credential leakage through screenshots, terminal history, pasted commands, or agent logs.
No suspicious patterns detected.