pyrofork-docs

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows and examples (e.g., SKILL.md and references/updates-and-filters.md and references/getting-started.md) explicitly instruct registering handlers, processing incoming Telegram messages/inline queries and inline-bot results — i.e., ingesting and acting on user-generated, third-party Telegram content — which could carry instructions that materially influence behavior.