Back to skill

Security audit

DaData.ru

Security checks for vulnerabilities and agentic risk

Overview

The skill’s DaData lookup purpose is coherent, but its setup instructions tell users to execute unverified remote installer scripts, which warrants Review before installation.

Review the oo CLI installation path before installing. Prefer an official package manager, pinned release, or downloaded installer with checksum/signature verification instead of executing curl | bash or irm | iex directly. Once the CLI is already installed and authenticated, the skill’s DaData actions are narrow read-style connector calls.

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:59
Finding
Unverified Remote Installer Downloaded and Executed Directly## Vulnerability Details **File Location**: `SKILL.md`, lines 59–63 **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 an external server and immediately execute their contents through Bash or PowerShell. The downloaded payload is not displayed for review, pinned to a specific version, or validated using a cryptographic checksum or signature. The installer source is not included in the audited project, so its effective behavior cannot be determined from the reviewed package. Although the URLs use HTTPS and an apparently related OOMOL domain, transport encryption does not mitigate compromise of the hosting infrastructure, DNS or account takeover, or subsequent replacement of the remote scripts. Direct remote execution is not necessary for the skill's declared DaData query functionality and exceeds the minimum privileges required to document or invoke connector operations. ### Attack Path 1. The `oo` command is unavailable and an agent or user follows the first-time setup instructions. 2. `curl` or `Invoke-RestMethod` downloads the current installer from the external OOMOL server. 3. The response is passed directly to Bash or `Invoke-Expression` without integrity verification or inspection. 4. If the hosting server, delivery path, or remote script has been compromised, attacker-controlled commands execute with the permissions of the invoking user. 5. Those commands can access resources available to that user and may install additional components or establish persistence. ### Impact Assessment Successful exploitation permits arbitrary command execution with the invoking user's privileges. The resulting sco ...[truncated 531 chars]
Remediation
## Remediation Suggestions - Remove the direct `curl | bash` and `irm | iex` installation patterns. - Distribute the CLI through a trusted package manager or a versioned release channel. - Pin installation instructions to a specific CLI version and immutable artifact. - Download the artifact without executing it, then verify a published cryptographic checksum or signature before installation. - Provide users with an opportunity to inspect the downloaded script or package before execution. - Require explicit user approval before installing software or running any installer. - Document the expected files, permissions, and system changes made by the installer. - Avoid requesting administrator or root privileges unless a specific installation step demonstrably requires them.
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
98% confidence
Finding
The skill instructs users to install software by piping a remote script directly into a shell, which creates a supply-chain and remote-code-execution risk if the hosting site, network path, or script content is compromised. Because the skill is operational guidance for tool execution, this context makes the pattern more dangerous: an agent or user may follow it verbatim during setup, executing unreviewed code on the host.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text says to use this skill for ANY DaData.ru request, which is overly broad and can cause the agent to invoke the skill whenever DaData is mentioned rather than when it is actually necessary and appropriate. In an adversarial setting, broad routing increases the chance of unintended tool use and can bypass more specific policy or safer alternatives.

Static analysis

No suspicious patterns detected.