pyrofork-best-practices

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

• Third-party content exposure detected (high risk: 0.70). The skill's runtime handlers and filters explicitly process Telegram updates and message content (see core-updates-handlers-propagation and features-filters-custom-filters in SKILL.md), meaning it ingests untrusted, user-generated content from the Telegram network which can directly drive actions (forward/reply/invoke raw API) and thus could enable indirect prompt-injection via malicious messages.