deep-research

Warn

Audited by Snyk on Sep 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The deep-research skill runs an autonomous multi-phase research pipeline where Phase 3 (RETRIEVE) executes multiple search CLI calls and spawns sub-agents to ingest unverified web pages, GitHub/forge repositories, and online articles without the user pre-selecting specific items.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 7, 2026, 09:39 PM
Issues
1
Security Audit — snyk — deep-research