mmk-notion-comment

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages a custom command-line interface (mmk) to interact with Notion API services.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by retrieving external comment data.
  • Ingestion points: The mmk notion comment list command retrieves user-generated comment text from Notion.
  • Boundary markers: No specific delimiters or safety instructions are defined in the skill markdown.
  • Capability inventory: The skill possesses write capabilities including adding and replying to comment threads.
  • Sanitization: The documentation lacks information regarding input validation or data sanitization for retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 03:28 PM
Security Audit — agent-trust-hub — mmk-notion-comment