telegram

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

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md and referenced playbooks, e.g., references/playbooks/digest.md) explicitly instructs the agent to fetch and read user-generated Telegram content via commands like msg list, msg search, and listen and then summarize/tag/respond based on that content, so untrusted third‑party messages can materially influence subsequent actions.