artifacts

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

• Third-party content exposure detected (medium risk: 0.30). The workflow sets up a webhook listener via registerTelegramTrigger in artifacts/automation/files/src/triggers/telegramTriggers.ts that receives and processes unverified incoming Telegram messages containing outsider free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The configuration references external fonts via unverified CDN URLs at runtime, establishing a weak/unknown external operational dependency.