polymarket

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to official Polymarket API domains including gamma-api.polymarket.com, clob.polymarket.com, and data-api.polymarket.com to retrieve market metadata, pricing, and trade information.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted data (market questions, descriptions) from external APIs.
  • Ingestion points: Data is fetched via scripts/polymarket.py using urllib.request and injected into the agent context for parsing and presentation.
  • Boundary markers: Absent; there are no specific markers or instructions to delimit external API content from agent instructions.
  • Capability inventory: The skill is limited to read-only network operations; it lacks any capabilities for file-system access, shell execution, or credential handling.
  • Sanitization: The script parses JSON and formats numeric data but does not perform content sanitization or filtering on string-based market descriptions.
  • [SAFE]: No malicious patterns were detected. The skill is strictly read-only and follows best practices for querying public data without requiring sensitive user credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:08 PM
Security Audit — agent-trust-hub — polymarket