polymarket

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and displays untrusted content from the Polymarket API, including market questions and descriptions. This represents a TIER_2 attack surface for indirect prompt injection, where a malicious market listing could attempt to influence the agent's behavior.
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/query.py) to perform its queries. The script uses the standard library urllib for network operations and correctly escapes user-provided parameters to prevent command or URL injection.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to gamma-api.polymarket.com, clob.polymarket.com, and data-api.polymarket.com. These are legitimate public API endpoints for the Polymarket prediction platform, and the operations are restricted to data retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:01 PM
Security Audit — agent-trust-hub — polymarket