inbox-triage
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
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 Step 2–3: the skill reads email thread content/snippets from the user’s inbox (messages authored by other people) and then classifies them, which requires the agent to ingest that email text for reasoning.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata