polymarket-trading

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the sports-skills CLI tool to manage orders and trades on the Polymarket platform. These commands are gated by explicit user confirmation requirements defined in the safety contract.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing the sports-skills Python package with the polymarket extra. This dependency is required for the skill's primary functionality and aligns with the author's namespace.
  • [DATA_EXFILTRATION]: The skill explicitly instructs the agent never to request or handle private keys, seed phrases, or wallet secrets within the chat context, directing users to local environment variables for secret management instead.
  • [PROMPT_INJECTION]: Instructions include defensive measures against automated or inferred execution, requiring specific token identifiers and explicit 'confirm' responses from the user before any order placement.
  • [DATA_EXPOSURE]: Market data and API outputs are treated as untrusted third-party content, with instructions to verify details with the user before performing high-risk actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:25 AM
Security Audit — agent-trust-hub — polymarket-trading