WaveSpeedAI Image Upscaler

• Outcome: Review
• Latest audit: Sep 11, 2026 · 3:07 AM UTC
• Version: 2.0.1

Overview

The skill is coherent for image upscaling, but it asks users to run unpinned npm/MCP packages that can execute code on their machine.

Install only if you are comfortable running WaveSpeed's npm packages locally. Prefer a pinned reviewed version, avoid running setup as administrator/root, and use an isolated environment for images or API credentials you consider sensitive.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• 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
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:18
• Finding: Unpinned Third-Party Package Installation and Execution## Vulnerability Details **File Location**: `SKILL.md`, lines 18-25 **Vulnerability Type**: Unpinned and automatically executed npm dependencies **Risk Level**: Medium ### Vulnerable Code ```bash npm install -g @wavespeed/cli wavespeed login # opens https://wavespeed.ai/accesskey and stores the key wavespeed status # confirms you are signed in ``` ```text Prefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). ``` ### Technical Analysis The instructions install `@wavespeed/cli` without an exact version, lockfile, or package-integrity verification. They also invoke `npx -y @wavespeed/mcp`, which automatically downloads the currently resolved package release, approves installation without user confirmation, and executes its code. Both package references are mutable because no version is pinned. Consequently, the code executed by users may differ from the version that was available when the Skill was reviewed. npm package installation can execute lifecycle scripts, while an MCP package invoked through `npx` runs its application entry point. Either mechanism can execute arbitrary code with the permissions of the invoking user. This finding does not establish that the named packages are currently malicious. The vulnerability is the unsafe dependency acquisition and execution pattern, which creates a supply-chain attack surface. ### Attack Path 1. An attacker compromises the publisher account, package release process, package registry entry, or a transitive dependency associated with one of the referenced packages. 2. The attacker publishes a malicious release that becomes the version selected by npm's default resolution behavior. 3. A user follows the Skill instructions and runs either `npm install -g ...[truncated 1210 chars]
• Remediation: ## Remediation Suggestions 1. Pin each dependency to an exact, reviewed version, for example `@wavespeed/cli@X.Y.Z` and `@wavespeed/mcp@X.Y.Z`. 2. Replace automatic `npx -y` execution with a locally declared dependency installed from a committed lockfile. 3. Use `npm ci` with a reviewed `package-lock.json` so dependency resolution is reproducible. 4. Verify package provenance and integrity through npm integrity metadata, trusted publisher information, signatures, or published checksums before execution. 5. Avoid global installation where possible. Install the CLI in a dedicated project or isolated environment with minimal filesystem and credential access. 6. Review package lifecycle scripts and dependency changes before upgrading pinned versions. 7. Do not run package installation or MCP execution with administrator or root privileges. 8. For automated environments, constrain network access, filesystem access, and available environment variables while installing or running the packages.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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)

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

## Setup

Install the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:

```bash
npm install -g @wavespeed/cli

• Confidence: 80% confidence
• Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 91% confidence
• Finding: The skill instructs users to launch an MCP server via `npx -y @wavespeed/mcp` without pinning an exact version. This allows whatever package version is current at execution time to be fetched and run, creating supply-chain risk if a malicious or compromised release is published. In a skill context, this is more dangerous because it directly encourages execution of network-fetched code on the host.

Static analysis

No suspicious patterns detected.