setup-assistant

Warn

Audited by Snyk on Apr 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly requires building and querying external public patent sources (SKILL.md requires an MPEP index and tests with "Search MPEP for claim definiteness requirements") and references live third‑party services (optional BigQuery, EPO OPS, and the USPTO fee-schedule URL in filing-reference.md), so the agent will ingest and act on open/public third-party content.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 10, 2026, 12:38 AM
Issues
1