E2B

• Outcome: Review
• Latest audit: Nov 3, 2026 · 11:20 AM UTC
• Version: 1.0.5

Overview

The E2B workflow includes approval safeguards, but its setup runs unverified remote code and omits the CLI’s automatic changes to other agent skills.

Review and install a verified CLI release yourself before enabling this skill. Its CLI can also install or refresh other agent skills; the publisher documents OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization. Connect only the intended E2B account and retain the write/delete approval safeguards. The remote installers and hosted connector were not verified.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The supplied command fetches and executes an Oomol installer, with no visible E2B interaction or demonstrated dependency relationship to E2B. This is an undeclared software-installation capability involving an inconsistent external resource. The downloaded script's precise effects cannot be determined from the provided chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High

• Category: Supply Chain
• Confidence: 98% confidence

Finding

The setup command pipes a remotely fetched, mutable script directly into Bash without verifying its integrity or reviewing it; the PowerShell alternative has the same risk. A compromised distribution endpoint could execute arbitrary code with the agent's local privileges, potentially stealing credentials or modifying files. The missing-CLI condition limits exposure, but the instructions do not require explicit approval before installation.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

• oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

  bash

  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  

  powershell

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 79)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