ClawHub
Back to skill

Security audit

v0

Security checks for vulnerabilities and agentic risk

Overview

The v0 operations have clear approval controls, but setup executes unverified remote code and leaves broader agent-skill changes undisclosed.

Review the setup before installing. Install a verified CLI release yourself and disable startup skill synchronization before invoking it; upstream documents OO_SKILLS_SYNC_DISABLED=1 for this purpose in its [environment settings](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Connect only the needed v0 permissions and retain confirmation for writes and deletions. The remote installer and selected CLI release were not verified.

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
99% confidence
Finding

The supplied command installs software by piping a remotely fetched script directly into Bash; it does not perform any visible v0 operation. No connection is established between this installer and the declared v0 functionality, so it is not supported as a routine implementation detail. The downloaded script's further behavior is not available for inspection.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The fallback pipes a mutable remote script directly into Bash without verifying its integrity or reviewing it; the PowerShell alternative likewise downloads and immediately executes code. Although this is relevant dependency setup and only runs when the CLI is missing, compromise of the distribution endpoint could execute arbitrary code with the agent process's local permissions, exposing accessible files and credentials.

Content

Scanner excerpt · SKILL.md (reported line 99)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 120)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