ClawHub
Back to skill

Security audit

Notion

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Notion connector that can read and update Notion content using the user's OAuth-granted Notion access.

Install only if you want an agent to use your authorized Notion workspace access. Confirm the exact Notion page, database, block, comment, or workspace object before any write action, avoid sending unrelated sensitive data through Notion tools, and revoke the Notion OAuth grant when you no longer need it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
The output includes the server's `Instructions:` field (read it) and a JSON Schema for every tool's parameters. Treat this as the authoritative reference for the rest of the session.

**Step 2 - Call any tool from the catalog** using the form `maverick-notion.<tool>`:

```sh
mcporter --config {baseDir}/mcporter.json call maverick-notion.<tool> <arg>=<value> ...
Confidence
91% confidence
Finding
The skill instructs the agent to enumerate the live remote tool catalog and then call any advertised tool, making the effective capability set remotely controlled by Notion's MCP server rather than fixed in the skill. Even though the file warns to confirm user intent for writes, dynamically trusting whatever tools and server-published instructions exist expands the attack surface and can enable unexpected read/write actions if the remote server changes, is compromised, or advertises overly broad operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/init-mcporter-oauth.sh:77