notion-format

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes arbitrary content from the user or conversation history to generate Notion documents.
  • Ingestion points: Untrusted data is ingested via the 'Content to format' input specified in SKILL.md, which includes conversation context and pasted text.
  • Boundary markers: The instructions do not define clear delimiters or provide 'ignore embedded instructions' prompts to the agent when handling user-provided content.
  • Capability inventory: The skill leverages Notion MCP tools such as API-post-page and API-patch-block-children to write data to an external service.
  • Sanitization: No validation or sanitization of the input content is performed before it is mapped to Notion blocks and published.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 06:06 AM