u301-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 instructs the agent to call RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS against the external Rube MCP/composio endpoints (e.g., https://rube.app/mcp and composio.dev/toolkits/u301) to fetch tool slugs, schemas and execution plans — i.e., it ingests third-party tool descriptions that the agent must read and act on, which could be untrusted content enabling indirect prompt injection.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the external MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and recommended execution plans that directly drive agent instructions and tool execution, so this external endpoint can control prompts/behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:02 AM