anki-mcp-server-integration

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to install the MCP server from the NPM registry (@ankimcp/anki-mcp-server) and optionally use ngrok for remote connectivity. These are well-known services and the downloads are standard requirements for the skill's operation.
  • [COMMAND_EXECUTION]: The setup documentation includes common shell commands for package installation and server configuration. These are transparently presented to the user as part of the initial environment setup.
  • [SAFE]: The skill possesses an indirect prompt injection surface as it processes data from Anki notes and decks via tools like findNotes and notesInfo. However, as flashcard content is typically user-controlled, this is considered an inherent characteristic of a study integration tool.
  • Ingestion points: Note and deck data are retrieved through findNotes and notesInfo tools defined in SKILL.md.
  • Boundary markers: Not explicitly mentioned in the processing logic.
  • Capability inventory: The skill can perform local file reads for media (storeMediaFile), network synchronization (sync), and database modifications (addNotes, updateNoteFields).
  • Sanitization: Not explicitly documented in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 04:58 AM
Security Audit — agent-trust-hub — anki-mcp-server-integration