anonyflow-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 instructs the agent to fetch and interpret tool schemas, execution plans, and connection data from public Composio/Rube MCP endpoints (e.g., RUBE_SEARCH_TOOLS via https://rube.app/mcp and composio.dev/toolkits/anonyflow), which are external public sources and therefore can supply untrusted, third-party content that the agent will read and act on.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and calling the Rube MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas and execute tools, so remote content from that URL can directly control agent instructions and execute code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:47 AM