cults-automation

Warn

Audited by Snyk on Feb 17, 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). This skill instructs the agent to call RUBE_SEARCH_TOOLS against the public Rube MCP (https://rube.app/mcp) and ingest returned tool schemas, recommended execution plans, and auth links from Composio toolkits, which are third-party/public content the agent is expected to read and act on, creating opportunity for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:37 AM