Skills
Navigate
skills/reason-machines/mcp-skills/office-oxide-mcp-rust-document-processor/Gen Agent Trust Hub

office-oxide-mcp-rust-document-processor

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to download and install a binary or package from an external source.
  • Evidence: Installation via cargo install office-oxide-mcp and binary downloads from https://github.com/Aimino-Tech/office-oxide-mcp/releases.
  • [REMOTE_CODE_EXECUTION]: The installation workflow involves downloading, building, and executing code from an external repository that runs as a local server with significant file system permissions.
  • Evidence: git clone https://github.com/Aimino-Tech/office-oxide-mcp.git followed by cargo build --release.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external files (Excel, Word, PowerPoint, and PDF), which could contain malicious instructions designed to manipulate the AI agent.
  • Ingestion points: office_read (extracting content from XLSX, DOCX, PPTX, PDF), office_list_pdf_fields, and office_analyze_pdf_layout.
  • Boundary markers: The instructions do not define boundary markers or delimiters to isolate untrusted document content from the agent's instructions.
  • Capability inventory: The skill has extensive capabilities including file system read/write, document modification, and image/chart insertion.
  • Sanitization: There is no evidence of sanitization or validation protocols to prevent embedded instructions in documents from influencing agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — office-oxide-mcp-rust-document-processor