polymarket

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (LOW): The skill documentation includes instructions to install the @polymarket/real-time-data-client package via npm. Although this package is not from an explicitly whitelisted trusted source, it is a scoped package directly related to the skill's primary function.
  • Indirect Prompt Injection (LOW): The skill is susceptible to Category 8 threats because it ingests and processes untrusted live data. * Ingestion points: Market data, trade activity, and user comments are received through the WebSocket connection's onMessage handler. * Boundary markers: Absent; there are no clear delimiters or instructions to the agent to ignore potentially malicious commands embedded in the external data. * Capability inventory: Based on the provided code, the skill is limited to monitoring and logging data; it does not exhibit dangerous capabilities like arbitrary code execution or file modification. * Sanitization: No sanitization or validation mechanisms are mentioned for the incoming data stream.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM