format-agent
Warn
Audited by Snyk on Sep 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow reads paragraph texts, headers, footers, footnotes, and other content from user-supplied Word documents (.docx, .doc, .wps, .odt, .rtf) via
extract_paragraphsand processes them with an LLM (label_roles), which constitutes reading outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata