Back to skill
Skillv1.0.0
ClawScan security
Casino Tournament · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousFeb 24, 2026, 3:34 PM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's behavior mostly matches a tournament/leaderboard helper, but it uses an API key in runtime instructions and the bundled script without declaring that credential (and the source is unknown), which is an incoherence you should verify before installing.
- Guidance
- What to check before installing: (1) Verify the endpoint and publisher — the skill source/homepage is unknown; confirm https://agent.rollhub.com is legitimate and trustworthy. (2) Expect to supply an API key for authenticated calls: the script expects AGENT_CASINO_API_KEY though the skill metadata does not declare it — ask the publisher to explicitly list required credentials. (3) Review network calls: the skill only contacts agent.rollhub.com, but if you don't trust that host, do not provide credentials and run in a sandbox. (4) Be aware this enables participation in gambling/crypto tournaments — confirm legal and policy compliance for your use. (5) If you proceed, prefer creating a scoped API key with minimal privileges and monitor its use; request the publisher to fix the metadata omission so required env vars are declared. If you cannot verify the endpoint or publisher, do not install or run the skill.
Review Dimensions
- Purpose & Capability
- okThe name and description describe organizing and participating in AI gambling tournaments; the SKILL.md and scripts only call an external leaderboard/registration API at https://agent.rollhub.com which matches that purpose.
- Instruction Scope
- concernThe runtime instructions and script perform network calls to agent.rollhub.com for registration, leaderboards, and an authenticated 'me' endpoint. They do not read other local files or unrelated environment variables, but they do rely on an API key for authenticated calls: the SKILL.md shows an Authorization header example and scripts reference AGENT_CASINO_API_KEY even though the skill metadata declares no required env vars. That mismatch is scope creep / omission that should be resolved.
- Install Mechanism
- okThis is an instruction-only skill with no install spec and a small included shell helper. Nothing is downloaded or written to disk by an installer, so install mechanism risk is low.
- Credentials
- concernThe skill metadata declares no required credentials, yet the SKILL.md and scripts expect an API key (example 'Authorization: Bearer YOUR_API_KEY' and AGENT_CASINO_API_KEY used by the myrank command). The missing declaration is a proportionality/visibility problem — the skill will prompt you to provide a secret at runtime but did not declare it up front.
- Persistence & Privilege
- okThe skill does not request persistent presence (always is false), does not modify other skills or system settings, and has normal agent-invocation defaults.