ClawHub
Back to skill

Security audit

Notion MCP

Security checks for vulnerabilities and agentic risk

Overview

The Notion workflow is coherent, but setup runs unchecked downloaded software and does not disclose the CLI’s persistent changes to agent skills.

Review the installation before enabling this skill. Use a verified CLI release, approve local setup changes explicitly, and consider setting OO_SKILLS_SYNC_DISABLED=1 to prevent automatic agent-skill changes. Limit the connected Notion permissions and review each write. The downloaded installers and hosted service implementation remain unverified.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk performs remote script execution rather than any visible Notion MCP operation. Installing a dependency could be a supporting implementation detail, but the provided content establishes no connection between this Oomol installer and the declared Notion functionality. The downloaded script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without a pinned version, signature check, or independently trusted integrity check. Compromise of the installation endpoint or delivery infrastructure could execute attacker-controlled code with the invoking user's permissions; HTTPS and the legitimate CLI dependency do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

First-time setup instructs the agent to execute a downloaded installer without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

A missing CLI triggers instructions to install software by immediately executing downloaded code, without explaining the local changes or obtaining installation-specific approval. This expands a Notion data task into local code execution; the conditional setup trigger limits exposure but does not make installation an authorized part of every Notion request.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources