Back to skill

Security audit

Recruitee

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Recruitee connector, but its setup instructions include running an unverified remote installer directly in a shell.

Review the setup commands before installing. Prefer installing the oo CLI through a verified, version-pinned package or inspecting and verifying the installer first. For write actions such as creating candidates, confirm the exact Recruitee payload before allowing the agent to run it.

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 Download and Immediate Execution## Vulnerability Details **File Location**: `SKILL.md`, lines 58-62 **Vulnerability Type**: Remote payload retrieval and execution **Risk Level**: Critical ### 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 documented installation procedures retrieve mutable scripts from an external server and immediately execute the responses through Bash or PowerShell. Neither procedure pins a specific installer version, verifies a cryptographic signature or checksum, nor gives the user an opportunity to inspect the downloaded content before execution. HTTPS protects the connection in transit but does not guarantee that the server, its publishing account, or the hosted installer has not been compromised. Because the executed content is retrieved at runtime, its effective behavior can change after the Skill has been reviewed. Installing the `oo` CLI is relevant when the required command is unavailable, but executing an unverified network response directly is not the minimum privilege or safest mechanism needed to perform that installation. A pinned and integrity-verified package can provide the same functionality without granting a mutable response an immediate code-execution channel. The separate connector commands transmit Recruitee payloads through the declared OOMOL service. That network behavior is consistent with the Skill's stated connector functionality, and the reviewed content does not establish covert transmission to an unrelated recipient. ### Attack Path 1. An agent attempts to perform a Recruitee operation and discovers that the `oo` command is unavailable. 2. The agent or user follows the first-time installation instructions in `SKILL.md`. 3. The command retrieves `install.sh` or `install.ps1` from the external OOMOL endpoint. 4. An attacker who ...[truncated 1225 chars]
Remediation
## Remediation Suggestions 1. Remove the `curl | bash` and `irm | iex` installation patterns. 2. Distribute the CLI through a trusted platform package manager or a versioned release artifact from a verified publisher. 3. Pin the installer or package to an explicit version rather than retrieving a mutable generic installation endpoint. 4. Publish a SHA-256 checksum or cryptographic signature through a separately protected channel and verify it before execution. 5. Download the artifact to a local file first, validate its expected origin and integrity, and only then execute or install it. 6. Require explicit user approval before downloading or installing software; an agent should not perform installation automatically after a failed connector command. 7. Execute installation with standard-user privileges whenever possible and clearly document any operation that genuinely requires elevation. 8. Prefer reproducible installation instructions similar to: ```bash curl -fSLo oo-installer.sh "https://trusted.example/releases/v1.0.2/install.sh" echo "EXPECTED_SHA256 oo-installer.sh" | sha256sum --check - bash oo-installer.sh ``` The placeholder host, release version, and checksum must be replaced with publisher-controlled, verified values. Equivalent signature or checksum validation should be required for PowerShell installations.
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 recommends installing software via a remote script piped directly into a shell (`curl ... | bash`). This is dangerous because it executes unverified code from the network without integrity checking, making compromise of the hosting site, CDN, DNS, TLS interception edge cases, or script supply-chain tampering immediately lead to arbitrary code execution on the user's machine.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The description says to use this skill for "ANY Recruitee request" and "Whenever a task involves Recruitee," which is a very broad activation condition. It does not provide limiting conditions or negative examples, so it could match loosely related mentions of Recruitee rather than clear, intentional invocations.

Static analysis

No suspicious patterns detected.