deep-research

Warn

Audited by Snyk on Mar 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 "Web Research Cascade" explicitly fetches pages via agent-browser / WebSearch / WebFetch and the Researcher "Community/Cases" shard requires crawling blog posts, conference talks and community discussions, meaning untrusted public web content (arbitrary URLs and user-generated posts) is ingested and used to form claims that can influence recommendations and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 01:12 AM
Issues
1
Security Audit — snyk — deep-research