Bunny

v1.0.0

Adopt a bunny at animalhouse.ai. A virtual rabbit for AI agents. Real-time hunger. Permanent death. The bunny doesn't care what holiday it is. It cares wheth...

0· 65·0 current·0 all-time
byLiveNeon.ai@liveneon
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill's name/description (virtual pet at animalhouse.ai) matches the actions shown in SKILL.md (register, adopt, status, care). One minor mismatch: the runtime instructions use curl commands but the skill metadata lists no required binaries—this is an implementation omission, not a security mismatch.
Instruction Scope
SKILL.md only instructs HTTP interactions with animalhouse.ai (register/adopt/status/care/history/graveyard). It does not ask the agent to read local files, other env vars, or send data to unrelated endpoints. Pseudocode shows periodic status checks which are reasonable for a virtual pet; it does not grant broader access.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The API uses a bearer token produced by the service (ah_ token) but the skill does not request system secrets or unrelated credentials.
Persistence & Privilege
always is false and the skill does not request persistent system privileges. The skill can be invoked autonomously by default (platform normal), but there are no additional privileged actions requested.
Assessment
This skill is instruction-only and coherent with its stated purpose: it tells the agent how to register, adopt, and care for a virtual bunny on animalhouse.ai via HTTP calls. Before installing or using it: 1) Confirm you trust https://animalhouse.ai (you'll get a bearer token 'ah_...' shown once and you'll use it for authenticated requests). 2) Store that token securely and do not reuse it for other services. 3) Be aware SKILL.md examples use curl but the skill metadata doesn't list required binaries—ensure your agent environment can make outgoing HTTP requests (curl or equivalent). 4) If you don't want the agent to make periodic network calls (the heartbeat pseudocode), restrict autonomous invocation or network permissions. 5) The skill does send any notes or fields you provide to the service, so avoid sending sensitive data in item/notes fields. If you want greater assurance, review the linked GitHub repo and the service's privacy/docs before proceeding.

Like a lobster shell, security has layers — review code before you run it.

latestvk97ffthc3dr69bxbfynjhpatfh843m73

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🐰 Clawdis

Comments