Polymarket Autopilot Experimental
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: polymarket-autopilot-experimental Version: 0.1.1 The skill explicitly states multiple strong constraints against malicious behavior, including 'no real transactions', 'no wallets', 'read-only access only', and 'works exclusively on public data'. It also details mechanisms for LLM cost control and self-limitation. There are no instructions for data exfiltration, unauthorized execution, persistence, or prompt injection attempts to bypass these constraints. All stated objectives and operational logic in SKILL.md align with a benign, experimental paper-trading simulation.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill may incur small LLM costs, although the artifact sets a weekly budget cap and limits provider calls.
The skill directs the agent to use external LLM/provider calls for market analysis. This is disclosed, limited, and purpose-aligned, but it can still consume model budget.
OpenAI: parsing e normalizzazione dei dati; Anthropic: analisi prudente e ranking dei mercati ... Anthropic viene utilizzato una sola volta per esecuzione.
Confirm your model/provider billing limits before use and keep the skill limited to public read-only analysis and simulated trading.