add-image-vision

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

• Third-party content exposure detected (high risk: 0.90). The skill downloads WhatsApp group image attachments and passes them to the agent as base64-encoded multimodal content blocks (see Phase 2 changes to src/* and Phase 4 verification in SKILL.md), so it ingests untrusted, user-generated third-party content that the agent interprets.