polymarket

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No patterns detected that attempt to override agent instructions or bypass safety filters. The language is purely instructional and focused on API integration.- [Data Exposure & Exfiltration] (SAFE): While the skill discusses sensitive credentials (Private Keys, API Keys), it explicitly warns against hardcoding them and provides standard environmental variable placeholders. No commands to exfiltrate data were found.- [Indirect Prompt Injection] (LOW): The skill interacts with external, untrusted data via the Polymarket Gamma and CLOB APIs. 1. Ingestion points: Market titles, event descriptions, and orderbook data fetched from polymarket.com subdomains. 2. Boundary markers: Not defined in this documentation. 3. Capability inventory: Includes market discovery, order placement, and position management. 4. Sanitization: Not mentioned in the README. This represents a standard surface for indirect injection if market metadata contains malicious prompts.- [External Downloads] (SAFE): The documentation links to official SDKs on GitHub (Polymarket organization). No automated installation scripts or piped remote execution patterns are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 08:12 PM