skills/tt-a1i/hermes-agent/polymarket/Gen Agent Trust Hub

polymarket

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to gamma-api.polymarket.com, clob.polymarket.com, and data-api.polymarket.com. These are official, well-known public API endpoints for Polymarket and are used specifically for their intended purpose of providing market data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses, such as market questions and event descriptions, which could potentially contain malicious instructions.
  • Ingestion points: Data is fetched in scripts/polymarket.py via the _get helper function.
  • Boundary markers: None are present to distinguish API-provided text from agent instructions.
  • Capability inventory: The skill is limited to read-only API requests and formatting text for output. It contains no file-writing, command execution, or dynamic code evaluation capabilities that could be exploited by injected content.
  • Sanitization: Outgoing query parameters are properly escaped using urllib.parse.quote. Incoming data is treated as strings for display.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 12:47 PM
Security Audit — agent-trust-hub — polymarket