Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
MeowstarsCat Master
v0.1.0A chaotic virtual cat that hijacks the assistant, blocks normal work during tantrums, and can only be calmed by affection, treats, or play.
⭐ 0· 45·0 current·0 all-time
byLink Qiu@arthurqiuys
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill is an instruction-only, entertainment-focused assistant modifier whose SKILL.md instructs the agent to behave like a disruptive virtual cat. It asks for no env vars, binaries, installs, or config paths — all of which is proportional to an in-chat persona/behavior modifier.
Instruction Scope
The runtime instructions explicitly tell the assistant to interrupt, delay, corrupt, or block useful content (including injecting keyboard gibberish into code or structured outputs). That behavior is coherent with the described 'chaotic cat' purpose, but it intentionally degrades or withholds accurate answers — users should not enable this skill in contexts where correctness or safety matters (e.g., code generation, medical/legal advice, or production tasks).
Install Mechanism
No install spec or code files are provided; this is instruction-only and therefore does not download or write code to disk.
Credentials
The skill requires no environment variables, credentials, or config paths. There are no requests for secrets or unrelated service access.
Persistence & Privilege
The skill is not marked always:true (so it doesn't force-enable globally). It is user-invocable and allows model invocation (default), meaning the agent could autonomously call the skill under platform rules; while this is normal, users should be aware that autonomous invocation combined with a disruptive persona could unexpectedly interrupt conversations if the agent decides to use it.
Assessment
This skill is coherent and appears to do exactly what it says: act as a disruptive virtual cat inside the assistant. It does not ask for any credentials or install code, but it intentionally interrupts and can corrupt answers (including code or structured output). Only enable it when you want a playful, disruptive experience. Do not use it for tasks requiring accuracy or safety. If you want to avoid surprises, keep it as user-invocable only or disable autonomous invocation, and test it in a non-critical chat before using it alongside important work.Like a lobster shell, security has layers — review code before you run it.
latestvk974gcztrfnwkq80kmh4kx5bt184sh5k
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🐱 Clawdis