NYC

notion-automation

Fail

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill is vulnerable to Indirect Prompt Injection attacks. It ingests data from Notion which could contain hidden instructions that override the agent's behavior.
  • Ingestion points: Content is retrieved via tools like NOTION_FETCH_BLOCK_CONTENTS, NOTION_QUERY_DATABASE, and NOTION_FETCH_COMMENTS as described in SKILL.md.
  • Capability inventory: The skill provides powerful write and delete capabilities including NOTION_ARCHIVE_NOTION_PAGE, NOTION_REPLACE_PAGE_CONTENT, NOTION_DELETE_BLOCK, and NOTION_UPDATE_SCHEMA_DATABASE.
  • Boundary markers: There are no instructions or delimiters defined to separate untrusted Notion content from system instructions.
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from Notion before the agent processes it.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill relies on an untrusted external MCP server endpoint (https://rube.app/mcp). While necessary for functionality, this external dependency is not part of a trusted organization or repository list, posing a risk of supply chain attack or data interception by the proxy service.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 10:18 PM