Back to skill
Skillv1.0.2
ClawScan security
hyperbot-quote · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 4, 2026, 7:01 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent: it documents read-only calls to a Hyperbot MCP server (SSE session + JSON-RPC tool calls) and does not request unrelated credentials, installs, or local access.
- Guidance
- This skill is internally coherent and only documents making read-only HTTP/S calls to mcp.hyperbot.network and several referenced data URIs (e.g., open.aicoin.com). Before installing, verify you trust the remote endpoints (check TLS certificate and domain reputation) and avoid sending any private keys, API secrets, or other sensitive data to the skill. Be aware that any wallet addresses or other inputs you provide will be transmitted to the listed external services for analysis. If you need stronger assurance, ask the publisher for an official homepage or source repo and confirm the endpoint ownership before use.
Review Dimensions
- Purpose & Capability
- okThe name/description (Hyperbot trading analytics) match the documented behavior: calling an MCP server for market, whale, and trader data. No unrelated environment variables, binaries, or config paths are requested.
- Instruction Scope
- okSKILL.md only instructs the agent to obtain a sessionId via SSE and call the MCP JSON-RPC endpoints (https://mcp.hyperbot.network/mcp and a few referenced data URIs). All actions are read-only and consistent with the stated analytics purpose. The instructions do not reference reading local files, secrets, or other system state.
- Install Mechanism
- okThis is an instruction-only skill with no install spec and no code files — lowest-risk from an installation perspective (nothing written to disk).
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. That is proportionate for a read-only analytics frontend that queries public/private endpoints via a sessionId.
- Persistence & Privilege
- okFlags show no forced persistence (always: false) and the skill does not request modification of other skills or system configuration. Autonomous invocation is allowed by default but is not combined with elevated privileges or secret access.