Back to skill

Security audit

KnowBe4

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent read-only KnowBe4 connector, but its setup instructions tell users to run remote installer scripts directly in a shell without verification.

Install only if you are comfortable trusting OOMOL's installer delivery path. Prefer reviewing the installer first, using a signed or package-manager install if available, and avoiding elevated shells. Once the oo CLI is installed and connected, the skill's KnowBe4 actions appear limited to read-only data access.

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 Installation Scripts Executed Directly by Shells## Vulnerability Details **File Location**: `SKILL.md`, lines 59–63 **Vulnerability Type**: Remote payload retrieval and immediate 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 scripts from externally controlled URLs and execute them immediately using `bash` or PowerShell's `Invoke-Expression`. No release version is pinned, and no cryptographic checksum or publisher signature is verified before execution. HTTPS protects the connection in transit but does not ensure that the script remains identical to the version reviewed during this audit. Compromise of the distribution server, hosting account, DNS infrastructure, TLS termination, or release process could cause arbitrary attacker-controlled commands to execute. Installing the `oo` CLI is relevant to first-time setup, but piping mutable network content directly into an interpreter exceeds the minimum privilege and trust necessary to accomplish that task. The audit found no evidence that the current remote scripts are malicious; the vulnerability is the unrestricted remote execution mechanism and its mutable supply-chain payload. ### Attack Path 1. The `oo` command is unavailable, causing the user or agent to follow the first-time setup instructions. 2. An attacker compromises or gains control over the remote installation endpoint or its supporting delivery infrastructure. 3. The attacker modifies `install.sh` or `install.ps1` to include malicious commands. 4. The documented command downloads the current payload without local inspection or integrity verification. 5. `bash` or `Invoke-Expression` immediately executes the attacker-controlled content. 6. The payload operates with all permissions available to the user running the ...[truncated 726 chars]
Remediation
## Remediation Suggestions Replace direct pipe-to-shell and `Invoke-Expression` installation with a verifiable installation process: 1. Pin the installer or binary to a specific reviewed release rather than a mutable URL. 2. Download the artifact to a local file without executing it automatically. 3. Publish and verify a fixed SHA-256 or stronger cryptographic digest through an independently protected channel. 4. Prefer signed release artifacts and validate the publisher signature before execution. 5. Allow the user to inspect the downloaded installer before explicitly approving execution. 6. Use a trusted platform package manager where available, with repository signature validation enabled. 7. Run installation with ordinary user privileges unless a documented operation strictly requires elevation. 8. Avoid automatically invoking installation as a fallback; display secure setup instructions and require explicit user approval.
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 software via a remote script piped directly into bash, which executes code fetched over the network without prior inspection or integrity verification. If the remote endpoint, delivery path, or hosting account is compromised, this becomes an immediate arbitrary code execution path on the user's machine.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description says to use this skill for ANY KnowBe4 request and instead of calling the API directly, which is an overly broad routing rule. This can cause an agent to invoke the skill in contexts beyond simple read-only retrieval, increasing the chance of unnecessary tool use, unintended data exposure, or bypass of safer task-specific handling.

Static analysis

No suspicious patterns detected.