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 (researcher agent)” step instructs searching public sources like npm/PyPI/GitHub/Web at runtime, which can ingest outsider-authored free text (e.g., package README/docs, issue/discussion content, scraped web pages) into the agent’s LLM context for evaluation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata