office-oxide-mcp-server

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to download a binary from a third-party GitHub repository (github.com/Aimino-Tech/office-oxide-mcp) or install it via cargo.
  • [REMOTE_CODE_EXECUTION]: The skill requires the installation and execution of an external Rust-native application (office-oxide-mcp) on the host system to provide its document processing functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external Office documents, creating a surface for indirect prompt injection.
  • Ingestion points: Content is read from external files via tools like office_read and office_list_pdf_fields in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or provide warnings for the agent to ignore instructions contained within the document data.
  • Capability inventory: The skill possesses numerous file-writing and modification capabilities, such as office_write_range, office_create_xlsx, and office_fill_pdf_form, as defined in SKILL.md.
  • Sanitization: There is no evidence of content sanitization or validation performed on the data extracted from the documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — office-oxide-mcp-server