parallel

Warn

Audited by Snyk on Mar 7, 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 performs web searches and extracts content from arbitrary public URLs via the Parallel.ai API (see SKILL.md "Content extraction from any URL" and the resource script's cmd_extract/call_api to /extract and cmd_search), so untrusted third‑party page content is ingested and can influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 03:11 AM