inbox-setup

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the user-pasted “S3.SAMPLES” step (“Paste 3–5 real sent emails from your inbox”); those emails are not authored by the operating user’s prompts and may include third-party content (e.g., other senders’ message bodies), which the skill then analyzes and incorporates into email-patterns.md.