notion-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest data from external Notion pages and databases, which creates a potential surface for indirect prompt injection. If an agent processes a Notion block containing malicious instructions, it could be influenced to perform unintended actions using the skill's capabilities.\n
  • Ingestion points: The tools NOTION_SEARCH_NOTION_PAGE, NOTION_FETCH_BLOCK_CONTENTS, and NOTION_QUERY_DATABASE mentioned in SKILL.md are used to pull external content into the agent context.\n
  • Boundary markers: The skill does not provide instructions to the agent to treat data from Notion as untrusted or to ignore embedded instructions (delimiters are absent).\n
  • Capability inventory: The skill provides significant write and delete permissions including NOTION_UPDATE_PAGE, NOTION_ARCHIVE_NOTION_PAGE, NOTION_INSERT_ROW_DATABASE, and NOTION_DELETE_BLOCK.\n
  • Sanitization: There are no requirements or mechanisms specified for sanitizing or validating content retrieved from Notion before it is used by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — notion-automation