twitch-automation

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly connects to the Twitch toolkit via Rube MCP (RUBE_MANAGE_CONNECTIONS, RUBE_SEARCH_TOOLS, RUBE_MULTI_EXECUTE_TOOL) and instructs fetching and paginating Twitch data, meaning the agent will ingest public, user-generated Twitch content (streams/chat) which could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:13 AM