deep-research

Warn

Audited by Snyk on Jun 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow (“Iterative Search” over at least 10 search rounds) necessarily fetches and reads public web/search results as readable text, which is outsider-authored content that can be injected into the LLM context via retrieved pages/snippets.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 01:44 AM
Issues
1
Security Audit — snyk — deep-research