Back to skill

Security audit

Google Drive

Security checks for vulnerabilities and agentic risk

Overview

This Google Drive skill is mostly coherent, but its first-time setup tells users or agents to run unverified remote installer scripts directly in a shell.

Review the installer path before installing. Prefer a verified package, pinned release, checksum, or manual inspection of the installer instead of running the provided one-line shell or PowerShell commands. Also confirm that you are comfortable routing Google Drive actions through OOMOL and require explicit approval for deletes, permission changes, and other write operations.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:97
Finding
Unverified Remote Installer Scripts Are Executed Directly## Vulnerability Details **File Location**: `SKILL.md`, lines 97–101 **Vulnerability Type**: Remote payload retrieval and execution **Risk Level**: Critical The first-time setup instructions download mutable scripts from an external server and immediately execute them: ```bash curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux ``` ```powershell irm https://cli.oomol.com/install.ps1 | iex # Windows PowerShell ``` ### Technical Analysis Both installation commands connect a network retrieval operation directly to a command interpreter. The downloaded content is not pinned to a specific release and is not checked against a cryptographic signature or checksum before execution. Consequently, the code ultimately executed can change after the Skill has been reviewed. HTTPS protects the connection in transit under normal conditions, but it does not mitigate compromise of the hosting service, publication pipeline, CDN, DNS infrastructure, or vendor account. Any party able to alter the remote installer can supply arbitrary shell or PowerShell commands. Installing the CLI when it is absent may be relevant to the declared Google Drive connector functionality. However, immediate execution of unverified remote content exceeds the minimum privilege and trust required to perform that installation. A separately downloaded, version-pinned, cryptographically verified package would provide the required functionality with substantially lower risk. ### Attack Path 1. The `oo` CLI is unavailable, causing an `oo: command not found` error. 2. The Agent follows the documented first-time setup instructions. 3. An attacker compromises or gains control over the installer hosting service, deployment pipeline, CDN, DNS path, or other mechanism capable of changing the response. 4. The attacker replaces the expected installer with a malicious shell or PowerShell payload. 5. `curl` or `irm` retrieves the attacker-contro ...[truncated 876 chars]
Remediation
## Remediation Suggestions 1. Remove both direct execution patterns (`curl | bash` and `irm | iex`). 2. Distribute the CLI through a trusted package manager or a versioned release hosted in the official project repository. 3. Pin installation instructions to a specific release rather than a mutable installer URL. 4. Download the package or script to a local file without executing it. 5. Publish a cryptographic checksum or, preferably, a signed release manifest through an independently protected channel. 6. Verify the checksum and signature before installation, and abort on any mismatch. 7. Allow the user or Agent to inspect the downloaded script before execution. 8. Execute the installer with ordinary user privileges unless a specific installation step demonstrably requires elevation. 9. If elevated privileges are required, isolate and document the exact command that needs them rather than running the complete remote installer as an administrator. 10. Document the external domains contacted and the data handled by the OOMOL connector so users can make an informed trust decision.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Content
- **`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
Confidence
97% confidence
Finding
The skill instructs the agent to install software by piping a remote script directly into a shell (`curl ... | bash`). This is a classic supply-chain and remote code execution risk: if the server, transport, or script is compromised, arbitrary code executes immediately on the host with the user's privileges.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill uses overly broad routing language instructing the agent to use it for ANY Google Drive request instead of calling the API directly. This can bypass more specific, safer tooling or policy checks and increases the chance the agent will invoke high-privilege operations through this skill without considering alternatives or narrower-scope controls.

Static analysis

No suspicious patterns detected.