search-first

Warn

Audited by Snyk on Jun 24, 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 workflow’s “Parallel Search” step instructs the researcher agent to search external sources (npm/PyPI/GitHub/Web) at runtime, which can return outsider-authored free-form text (e.g., README/docs/issues scraped from those sites) into the agent’s LLM context for evaluation.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 24, 2026, 12:59 PM
Issues
1
Security Audit — snyk — search-first