Back to skill

Security audit

Notion MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed Notion read/search connector, but its fallback setup tells the agent to run an unverified remote installer script, which is too powerful for this purpose.

Install only if you are comfortable with OOMOL mediating access to your Notion data and with the oo CLI setup. Prefer installing the CLI manually from a trusted source and verifying it yourself before using the skill; do not let an agent run the remote installer automatically.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes capability to install software by executing remote bootstrap commands, which is significantly more powerful than its stated purpose of reading/searching Notion data. This creates a path from a benign data-access task to arbitrary code execution on the host, especially dangerous in an agent context where users may not realize installation side effects are in scope.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

curl ... | bash executes code fetched live from a remote server without verification, review, or integrity pinning. In an agent workflow this is especially risky because compromise of the distribution endpoint, network path, or installer content could lead to full host compromise under the agent's execution privileges.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is presented as a read/search interface for Notion, but it also instructs the agent to perform authentication and connection bootstrap steps. Expanding operational scope beyond the declared purpose can cause agents to take account-affecting actions the user did not explicitly request, increasing the risk of unsafe delegation and unexpected credential or environment changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.