jarvis-mission-control

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted, user-generated content from public channels (Telegram, incoming/outgoing webhooks, GitHub issues) and the agent-bridge/webhook flows auto-create and act on tasks from that content (see CLAUDE.md "Agent Notifications" and webhook registration, .claude/skills/architecture.md and .mission-control/integrations/README.md describing the Telegram bridge and webhook handling, plus agent-bridge auto-creation behavior), so external third-party messages can materially influence agent actions.