patent-architect

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 Prior Art Search (SKILL.md Steps 2.2–2.4) explicitly fetches and ingests open-web/public patent and technical pages via SerpAPI/Exa.ai and Claude's WebSearch (and Step 2.5 synthesizes those results into novelty/decisioning), so untrusted third‑party content is read and can materially influence the agent's analysis and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 09:42 AM
Issues
1