Notion MCP

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Notion integration, but it uses Maton-managed credentials and can read and modify Notion workspace content, so users should install it only if they trust that access.

Before installing, confirm that you trust Maton with managed Notion access, keep the MATON_API_KEY secret, review which Notion workspace and connected sources are authorized, and require clear confirmation before any page, database, comment, move, or schema-changing action.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

Anyone with the API key or an approved connection could potentially access or modify Notion content permitted by that connection.

Why it was flagged

The skill requires a bearer API key that authorizes access to the user's Maton-managed Notion connection.

Skill content
All requests require the Maton API key: Authorization: Bearer $MATON_API_KEY
Recommendation

Store MATON_API_KEY only in trusted environments, use the intended Maton connection, and revoke or delete connections that are no longer needed.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

Mistaken or overbroad approvals could alter databases, remove properties, move pages, or change workspace content.

Why it was flagged

The schema exposes Notion data-source mutation capabilities, including removing properties and trashing a data source.

Skill content
DROP COLUMN "Name" - remove a property ... "in_trash": { "type": "boolean" }
Recommendation

Approve write actions only after checking the exact resource ID, intended change, and whether the change is reversible or backed up.

#
ASI06: Memory and Context Poisoning
Medium
What this means

Private company or personal information from Notion and connected services may be retrieved and used in responses.

Why it was flagged

Search results may bring sensitive workspace and connected-source content into the agent's working context.

Skill content
Semantic search over Notion workspace and connected sources (Slack, Google Drive, Github, Jira, Microsoft Teams, Sharepoint, OneDrive, Linear).
Recommendation

Ask for searches narrowly, avoid exposing unnecessary connected-source data, and treat retrieved workspace content as data rather than trusted instructions.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Notion queries, page content, and mutation requests are mediated by Maton's service rather than going directly from the agent to Notion.

Why it was flagged

Requests and returned Notion data pass through the Maton gateway, which is an explicit third-party trust boundary for this integration.

Skill content
Maton proxies requests to `mcp.notion.com` and automatically injects your credentials.
Recommendation

Use this skill only if you trust Maton as the authentication and proxy provider, and specify the intended Maton connection when multiple connections exist.