parallel-research

Warn

Audited by Snyk on Feb 24, 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 ingests and relies on public web content—Parallel AI Chat/Deep Research endpoints that return web citations (references/api-guide.md and SKILL.md) and direct scraping of vendor pages via scripts/vendor_selection.py -> scrape_page—which are parsed and used to drive scoring, enrichment, and recommendation actions, so untrusted third‑party content can materially influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 04:22 AM