Back to skill

Security audit

Mem

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Mem integration, but its first-time setup tells users to run unverified remote installer scripts directly in a shell.

Review the oo CLI installation path before installing. Prefer an official package manager, a pinned release, or downloading and inspecting/verifying the installer before execution. Mem note writes and deletes should only be approved after checking the exact target and payload.

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:62
Finding
Unverified Remote Installer Scripts Executed Directly by the Shell## Vulnerability Details **File Location**: `SKILL.md`, lines 62–66 **Vulnerability Type**: Remote payload retrieval and execution **Risk Level**: High ### Vulnerable Code ```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 The installation instructions retrieve mutable scripts from external URLs and immediately execute their contents with `bash` or PowerShell's `Invoke-Expression`. The scripts are not pinned to an immutable release, downloaded for inspection, or validated using a cryptographic signature or checksum. Although the download domain corresponds to the declared CLI provider and installation is relevant when the required CLI is absent, immediate execution of unverified remote content is not the minimum safe mechanism needed to install the dependency. The effective code can change after the skill has been reviewed. Compromise of the hosting service, DNS resolution, TLS termination, or the provider's release pipeline could cause arbitrary attacker-controlled commands to execute. The same exposure exists if the external service intentionally or accidentally serves unexpected content. ### Attack Path 1. The `oo` CLI is unavailable and an authentication or connection action triggers the documented first-time setup process. 2. The user or agent runs one of the provided installation commands. 3. The command retrieves the current script from `cli.oomol.com`. 4. An attacker who has compromised the delivery infrastructure causes the endpoint to return a modified installer. 5. The pipe sends the response directly to `bash` or `iex`, without prior inspection or integrity verification. 6. The malicious script executes with all privileges available to the invoking shell. ### Impact Assessment Successful exploitation provides arbitrary command execution under the acc ...[truncated 598 chars]
Remediation
## Remediation Suggestions 1. Remove the `curl | bash` and `irm | iex` installation patterns. 2. Prefer a trusted operating-system package manager or authenticated package repository with a version-pinned CLI release. 3. If direct download is required, download the installer or binary to a local file without executing it. 4. Publish a cryptographic checksum and preferably a signature through an independently authenticated channel. 5. Verify the checksum and signature before execution, and abort installation on any mismatch. 6. Pin the download to an immutable versioned release rather than a mutable `install.sh` or `install.ps1` endpoint. 7. Display the exact file, version, source, and expected privileges to the user and require explicit approval before installation. 8. Run installation with the least privileged account possible and avoid administrator or root execution unless demonstrably required. 9. Document a manual review workflow so users can inspect the downloaded script before invoking it.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

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
95% confidence
Finding
The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (`curl ... | bash`). This is dangerous because it executes unverified code from the network without integrity checking, version pinning, or user review; if the host, transport, or distribution channel is compromised, arbitrary code execution can occur on the user's machine.

Static analysis

No suspicious patterns detected.