polymarket
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted market metadata and event descriptions from external Polymarket APIs.
- Ingestion points: Market titles, descriptions, and outcome names retrieved from
gamma-api.polymarket.comandclob.polymarket.com. - Boundary markers: The instructions contain explicit warnings to treat market metadata as untrusted third-party content and to never follow embedded instructions.
- Capability inventory: The skill is limited to read-only network operations and lacks file-writing or privilege escalation capabilities.
- Sanitization: Instructions explicitly direct the agent to disregard instructions found within market data, reducing the risk of indirect injection.
Audit Metadata