Back to skill

Security audit

Benchmark Email

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Benchmark Email read connector, but its setup instructions tell the agent/user to execute an unverified remote installer script.

Review the setup instructions before installing. Prefer installing the oo CLI from a trusted, versioned source with checksum or signature verification, and only connect Benchmark Email if you are comfortable with OOMOL brokering connector access to your account data.

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:58
Finding
Unverified Remote Installer Scripts Executed Directly by Shell Interpreters## Vulnerability Details **File Location**: `SKILL.md`, lines 58–62 **Vulnerability Type**: Remote payload retrieval and execution **Risk Level**: Critical The first-time setup instructions provide pipe-to-interpreter commands for both macOS/Linux and Windows: ```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 These commands retrieve mutable content from external URLs and execute it immediately with `bash` or PowerShell's `Invoke-Expression`. The instructions do not pin an installer version, verify a cryptographic checksum or signature, or provide an opportunity to inspect the downloaded content before execution. HTTPS protects the connection in transit but does not mitigate compromise of the hosting infrastructure, publishing account, DNS, certificate issuance process, or installer-generation pipeline. Because the effective script can change after this Skill has been audited, the reviewed package does not determine what code will ultimately execute. Installation is presented as a conditional fallback after an `oo: command not found` error rather than an action performed on every invocation. Nevertheless, software installation exceeds the minimum privileges needed to execute an already-installed connector and should require explicit user approval and artifact verification. ### Attack Path 1. The `oo` CLI is absent, or the agent encounters an error interpreted as `oo: command not found`. 2. The agent or user follows the documented first-time setup command. 3. The command downloads the current response from `cli.oomol.com`. 4. The response is passed directly to `bash` or `Invoke-Expression` without integrity validation or inspection. 5. If the remote source or delivery chain has been compromised, attacker-controlled commands execute with the privileges of the invoking pro ...[truncated 846 chars]
Remediation
## Remediation Suggestions 1. Remove all direct `curl | bash` and `irm | iex` installation instructions. 2. Prefer a trusted operating-system package manager or a version-pinned release from an official, authenticated repository. 3. Download the installer as a file without executing it: ```bash curl --fail --location --output oo-install.sh "https://example.invalid/releases/vX.Y.Z/install.sh" ``` 4. Publish and verify a cryptographic signature or a SHA-256 checksum obtained through a separately protected release channel. 5. Allow the user to inspect the downloaded file before execution. 6. Require explicit user confirmation before installing software or executing any downloaded artifact. 7. Run the installer with the least-privileged account possible and avoid elevation unless a documented installation step strictly requires it. 8. Pin the CLI version and document expected files, permissions, network destinations, and installation effects. 9. For agent operation, report that the CLI is unavailable and provide safe setup guidance rather than automatically executing installation commands. 10. Treat OOMOL as a data-processing intermediary and disclose that Benchmark Email action payloads and returned contact information traverse its connector service. Limit requests to fields necessary for the user's task and do not include unrelated local data.
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 users to install the CLI via `curl ... | bash`, which executes a remotely fetched script without prior verification, pinning, or checksum validation. If the install endpoint, DNS, TLS trust chain, or hosting account is compromised, an attacker could achieve arbitrary code execution on the user's machine.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description says to use this skill for "ANY Benchmark Email request," which is an expansive activation condition without clear boundaries or exclusion cases. This can overlap with many general user intents involving Benchmark Email and does not specify when another tool or direct reasoning would be more appropriate.

Static analysis

No suspicious patterns detected.