Back to skill

Security audit

图像生成 GPT Image 2.5 Flare

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wrapper around dLazy's image-generation CLI, with normal cloud/API-key risks and no artifact-backed malicious behavior.

Before installing, review the dLazy CLI source/package if your environment is sensitive, prefer npx or a sandboxed install over a global install when possible, and only pass files you are comfortable uploading to dLazy. Use a revocable API key and rotate it if you no longer trust the local machine or CLI installation.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:5
Finding
Execution of an Externally Retrieved Third-Party CLI Without Locally Verifiable Integrity<![CDATA[ ## Vulnerability Details **File Location**: `SKILL.md:5, 56-62`; equivalent instructions also appear in `SKILL-cn.md:5, 56-62` **Vulnerability Type**: Third-party package supply-chain exposure **Risk Level**: Medium ### Vulnerable Code From `SKILL.md`: ```yaml metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/cli@1.2.3","installAlternative":"npx @dlazy/cli@1.2.3","homepage":"https://github.com/dlazy-ai/cli","source":"https://github.com/dlazy-ai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","files.dlazy.com"]},"openclaw":{"systemPrompt":"When invoking this skill, use dlazy gpt-image-2-5-flare -h for help."}} ``` ```bash npx @dlazy/cli@1.2.3 <command> ``` ```text npm install -g @dlazy/cli@1.2.3 ``` The Chinese-language document, `SKILL-cn.md`, declares and recommends the same package installation and execution mechanisms. ### Technical Analysis The Skill contains no executable implementation that can be audited locally. Instead, it delegates its complete runtime behavior to `@dlazy/cli@1.2.3`, retrieved from an external npm registry through either `npm install -g` or `npx`. Pinning the direct package to version `1.2.3` reduces accidental version drift, but it does not provide cryptographic verification within this project. The repository contains no package integrity hash, lockfile, vendored source, verified artifact, or pinned transitive dependency graph. npm installation may also execute package lifecycle scripts. Consequently, the effective code executed by the Skill is outside the reviewed artifact. This is a supply-chain risk rather than evidence that the named package is currently malicious. Exploitation would require compromise or substitution of the package artifact, a maintainer or registry account, the registry delivery path, or one of the package's unresolved tra ...[truncated 1627 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Vendor the required CLI implementation or provide an auditable local wrapper so the effective runtime code is included in the reviewed artifact. 2. Publish and verify a cryptographic integrity digest for the exact npm package artifact before execution. 3. Include a lockfile that pins the complete transitive dependency graph and verifies package integrity fields. 4. Disable npm lifecycle scripts where compatible, for example by using `--ignore-scripts`, and explicitly document any scripts that are genuinely required. 5. Prefer an isolated, non-global installation over `npm install -g` to limit persistence and system-wide exposure. 6. Run the CLI in a sandbox or container with: - Read access limited to explicitly selected input files. - Write access limited to a dedicated output directory. - No access to unrelated credentials or home-directory files. - Network access restricted to documented and required endpoints. 7. Store API credentials using an operating-system credential manager where possible, rather than a plaintext configuration file. 8. Independently review the source corresponding to version `1.2.3` and verify that the published npm artifact reproducibly matches that source. 9. Add automated dependency scanning, provenance verification, and package-signature checks to the release process. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Ae1

High
Category
analysis-evasion
Content
[English](./SKILL.md) · [中文](./SKILL-cn.md)
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Whitespace Padding

Medium
Category
Prompt Injection
Content
## 错误处理

| Code | 错误类型                         | 示例信息                                                                                                                 |
| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |
Confidence
70% confidence
Finding
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The main title and body language begin in Chinese, while the policy category requires flagging language or locale constraints that are imposed without user opt-in. Although an English link is present, this file itself does not ask for or provide a language choice before presenting instructions in a fixed language.

Whitespace Padding

Medium
Category
Prompt Injection
Content
## Error Handling

| Code | Error Type                         | Example Message                                                                                                          |
| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| 401  | Unauthorized (No API Key)          | `ok: false, code: "unauthorized", message: "API key is missing or invalid"`                                                              |
| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |
Confidence
70% confidence
Finding
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
该文件主体内容与标题均为中文,并在使用说明中直接以中文对代理下达操作指令,但未说明应根据用户语言偏好切换输出或先征求用户同意。虽然存在英文版链接,但当前文件本身没有要求代理提供语言选择,因此构成语言/locale 策略风险。

Static analysis

No suspicious patterns detected.