Credit Repair Cloud

• Outcome: Review
• Latest audit: Sep 15, 2026 · 4:08 AM UTC
• Version: 1.0.2

Overview

This is a coherent Credit Repair Cloud connector, but its setup instructions tell users to run unverified remote installer scripts.

Review the OOMOL oo CLI installation path before installing. Prefer a signed or checksum-verified installer over the documented direct shell execution, and only approve Credit Repair Cloud write or delete actions after checking the exact records and payloads.

A.I.G

Vulnerability Patterns

• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

• Location: SKILL.md:62
• Finding: Unverified Remote Installation Scripts Executed Directly by Shells<![CDATA[ ## 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 an external URL and immediately execute their contents with `bash` or PowerShell's `Invoke-Expression`. There is no release pinning, cryptographic signature validation, checksum verification, or opportunity to inspect the downloaded files before execution. Although installation is presented as a conditional first-time setup step and the scripts are hosted on an OOMOL domain, the effective code executed by these commands can change after the Skill has been reviewed. Compromise of the hosting service, DNS resolution, TLS or release infrastructure, vendor account, or installation pipeline could therefore convert the documented setup process into arbitrary code execution. The PowerShell form has the same security property as the Unix command: data returned by the network endpoint is interpreted directly as executable code. ### Attack Path 1. The `oo` CLI is unavailable, causing an `oo: command not found` error. 2. The user or Agent follows the Skill's first-time setup instructions. 3. The command downloads the current contents of `install.sh` or `install.ps1`. 4. A compromised server, distribution pipeline, or other trusted delivery component supplies attacker-controlled script content. 5. The shell immediately executes that content without validating its identity or integrity. 6. The payload inherits the permissions and accessible environment of the user running the installation command. ### Impact Assessment Successful exploitation permits arbitrary command execution with the invoking user's privileges. Depending on tho ...[truncated 528 chars]
• Remediation: <![CDATA[ ## Remediation Suggestions 1. Remove direct `curl | bash` and `Invoke-RestMethod | Invoke-Expression` execution patterns. 2. Pin installation instructions to a specific, immutable CLI release and versioned artifact. 3. Download the installer or binary to a local file before execution. 4. Publish and verify a SHA-256 or stronger cryptographic digest over the downloaded artifact. 5. Prefer vendor-signed packages and verify the signature against a documented, independently distributed signing key. 6. Use an operating-system package manager or a trusted release repository where package integrity and provenance are validated. 7. Require explicit user approval before installing software or granting elevated privileges. 8. Provide an inspection step before execution and fail closed if verification is unavailable or unsuccessful. 9. Keep installation outside normal connector execution so ordinary Credit Repair Cloud operations cannot trigger software installation automatically. A safer conceptual workflow is: ```bash # Download a pinned release without executing it. curl -fL -o oo-installer.sh "https://trusted.example/releases/<fixed-version>/install.sh" # Compare against a separately published, pinned digest. printf '%s %s\n' '<expected-sha256>' 'oo-installer.sh' | sha256sum --check - # Execute only after successful verification and explicit approval. bash oo-installer.sh ``` Equivalent signature or checksum validation should be required for the Windows installer. ]]>

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive 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 `curl ... | bash`, which executes a remote script directly from the network without prior verification, pinning, or integrity checks. If the remote host, distribution path, TLS trust chain, or installation script is compromised, the user may execute arbitrary code on their machine.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger text instructs the agent to use this skill for "ANY Credit Repair Cloud request," which is overly broad and can cause automatic invocation for a very wide set of user prompts, including ambiguous or high-risk ones. In a skill that supports read, write, and destructive operations, broad routing increases the chance of unintended data access or modification without sufficient narrowing or confirmation.

Static analysis

No suspicious patterns detected.