p-image

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

• Third-party content exposure detected (low risk: 0.10). The skill is a CLI wrapper where outsider-provided free text is the user’s own --input JSON prompt (and optional image URLs), but the workflow does not describe any automatic ingestion of third-party community/email/chat/GitHub/Jira text without first selecting a specific user-supplied item.