ma-end-to-end
Warn
Audited by Snyk on Jun 18, 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). Stage 02/03/04/05 rely on outsider-authored free text from public web content and downloaded PDFs (e.g., search results and full-text PDFs) that are ingested into LLM context via the referenced skills (e.g.,
/ma-search-bibliography,/ma-screening-quality,/ma-fulltext-management,/ma-data-extraction) for screening/extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata