parallel-search

Warn

Audited by Snyk on Feb 16, 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 uses the Parallel Search API (see SKILL.md and scripts/parallel-client.ts where client.beta.search is called) to retrieve ranked URLs and extended excerpts from the open web, and those untrusted third-party excerpts are read and synthesized by the agent (see scripts/search.ts and scripts/formatter.ts), exposing it to indirect prompt injection via web-sourced content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:57 AM