prior-art-search

Warn

Audited by Snyk on Mar 28, 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 explicitly fetches and ingests public patent documents from third‑party sources (Google BigQuery Patents Public Data and the USPTO API) as shown in SKILL.md ("Databases", "Required Data Access") and in prior_art_types.py (search_prior_art and get_patent_details), and it reads and interprets those documents to drive patentability assessments, IDS lists, and claim-drafting decisions, so untrusted third‑party content can materially influence agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 02:28 AM
Issues
1