telegram-automation

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-generated Telegram content via calls like TELEGRAM_GET_UPDATES and TELEGRAM_GET_CHAT_HISTORY (see "5. Forward Messages and Get Updates" and "Common Patterns" sections), which are untrusted third-party messages that the agent is expected to read and use to drive actions (forwarding, replying, setting commands), 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 connecting to the Rube MCP server (https://rube.app/mcp) and explicitly instructs calling RUBE_SEARCH_TOOLS to fetch current tool schemas at runtime, which directly supply the tool definitions that control the agent's prompts/instructions, so this is a runtime dependency that can control agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:20 AM