diadoc-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions utilize the uvx command to fetch and execute the diadoc-mcp-ru package from a public registry at runtime.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests untrusted data from the Diadoc API, including document content, counterparty messages, and metadata, which are processed by the agent.
  • Boundary markers: The instructions do not specify any boundary markers or instructions for the agent to ignore potential malicious content embedded within the documents.
  • Capability inventory: The skill provides a significant capability surface with 114 methods, including signing and sending documents.
  • Sanitization: There is no evidence of sanitization or filtering of the external data before it is presented to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:51 AM
Security Audit — agent-trust-hub — diadoc-mcp