opendocswork-mcp-office-processing
Warn
Audited by Snyk on Jun 13, 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 required runtime workflow for this skill is to read/parse user-supplied Office/PDF files via MCP tools like
office_read/office_list_pdf_fields, and the extracted document text (authored by whoever created the file, i.e., an outsider) is ingested into the agent’s LLM context as JSON/Markdown/Text output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata