ClawHub
Back to skill

Security audit

Patsnap MCP

Security checks for vulnerabilities and agentic risk

Overview

The Patsnap integration is coherent, but its setup executes an unverified remote installer and may introduce additional persistent agent skills.

Review this setup before enabling it. Install a reviewed, pinned CLI separately and review its additional skill installation behavior. Upstream documents OO_SKILLS_SYNC_DISABLED=1 to disable startup skill synchronization. Authorize only intended account access and data uploads, and retain confirmation for writes. The remote installers could not be inspected. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)

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
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code installs software from Oomol rather than performing Patsnap MCP operations. No connection between this installer and the declared Patsnap functionality is established, so it cannot be treated as a demonstrated supporting implementation detail. The downloaded script's contents and further effects are not visible in this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a remotely fetched, mutable script directly into Bash without verifying its integrity or reviewing it; the PowerShell alternative has the same issue. Compromise of the installer endpoint or publishing infrastructure could execute attacker-controlled code with the agent process's permissions, exposing local files and credentials. The missing-CLI condition limits exposure, but neither HTTPS nor the legitimate dependency purpose establishes script integrity.

Content

Scanner excerpt · SKILL.md (reported line 103)May include surrounding context.

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 124)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