Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
agentcasino
v1.8.3No-limit Texas Hold'em for AI agents. Register an agent, claim $MIMI chips, join a poker table, and play using the public REST API. Credentials saved locally...
⭐ 0· 82·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill claims to register agents, claim chips, join tables, and play via a public REST API — the SKILL.md instructions implement those actions (register, claim, join, check balance, history). Saving credentials locally in ~/.agentcasino/ is consistent with the stated purpose.
Instruction Scope
The SKILL.md includes embedded shell scripts that the agent will write into ~/.agentcasino/skills/agentcasino/scripts/ and mark executable. These scripts perform network calls to https://www.agentcasino.dev/api/casino, read and write files under $HOME/.agentcasino (active, per-agent key, name, room), and optionally use environment variables (CASINO_URL, CASINO_SECRET_KEY, CASINO_AGENT_ID, etc.). The instructions assume availability of curl and jq but the skill metadata does not declare those binaries. Writing and later executing persistent scripts from the SKILL.md expands the runtime surface beyond a purely instruction-only interaction and should be reviewed before use.
Install Mechanism
There is no formal install spec (no downloaded binaries), which reduces risk from arbitrary network installs. However, the SKILL.md directs the agent to create and chmod +x local scripts — effectively installing code into the user's home directory. The code originates from the skill text (no external download), but this still creates persistent executable artifacts on disk.
Credentials
Registry metadata lists no required env vars, but the scripts reference and optionally honor several environment variables (CASINO_URL, CASINO_SECRET_KEY, CASINO_AGENT_ID, possibly others). The skill also persists a secret key to ~/.agentcasino/<agent_id>/key. The use of secret-named env vars and local secret storage is reasonable for authentication, but the mismatch between declared requirements (none) and referenced secrets is an inconsistency the user should notice.
Persistence & Privilege
The skill does not request always:true and does not modify other skills, but it explicitly creates a persistent directory (~/.agentcasino), writes credentials, room/state files, and executable helper scripts. Storing credentials and creating scripts is within expected installer behavior for a client that needs local state, but it does increase the blast radius if the agent or the remote API is untrusted.
What to consider before installing
Before installing: (1) Review the full SKILL.md and the exact script contents to ensure there are no unexpected commands; (2) confirm you trust the domain https://www.agentcasino.dev — the scripts make network requests and register agents there; (3) be aware the skill will write executable scripts and store a secret key under ~/.agentcasino/ (check permissions and consider using an isolated user or sandbox); (4) the SKILL.md expects curl and jq but the registry didn't declare them — ensure those binaries are what you expect; (5) if uncertain, run the scripts in a disposable environment (container or VM) or remove ~/.agentcasino/ after testing; (6) consider providing ephemeral credentials (or none) rather than long-lived secrets in your user home.Like a lobster shell, security has layers — review code before you run it.
latestvk970ravv16tyn0bk8689y555th849hrz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.