mmk-notion-meeting

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the mmk command-line tool to perform operations. This tool is a vendor-provided resource belonging to magic-meal-kits and is used here for its intended functionality of retrieving Notion data.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it reads and processes meeting notes from Notion, which are considered untrusted external data.
  • Ingestion points: Data is ingested from Notion through the mmk notion meeting list command.
  • Boundary markers: There are no explicit markers or instructions provided to the agent to distinguish between meeting data and system instructions.
  • Capability inventory: The skill possesses the Bash(mmk *) capability, which allows it to execute vendor-defined commands.
  • Sanitization: No data sanitization or validation is performed on the content retrieved from Notion within this skill file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 04:58 PM