Back to skill

Security audit

MetaDig Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because it directs the agent to run unverified online installation scripts, including during troubleshooting.

Require your approval for installation and upgrades, and prefer a fixed CLI release with verified authenticity. Selected reference media is uploaded and receives public URLs, so avoid confidential inputs. Confirm credit costs and keep tokens out of conversations. All bundled documents were reviewed, but the downloaded installers and CLI behavior remain unverified.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The command exposes a file-upload capability rather than AI generation or the listed queries. Although it uses the declared MetaDig platform, transferring user-provided local files is a distinct capability, not merely saving generated outputs to a canvas project. The snippet does not establish that any upload was actually executed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command fetches an unpinned installer and immediately executes its contents in Bash. If the hosted script is compromised or changed maliciously, it can access local files and credentials or modify the environment with the executing user's permissions.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

bash
# macOS / Linux
curl -fsSL https://waytometa.cn/cli/install.sh | bash

# Windows PowerShell
iwr https://waytometa.cn/cli/install.ps1 -useb | iex

Chaining Abuse

High
Category
Tool Misuse
Confidence
99% confidence
Finding

This pipeline promotes downloaded network content directly into executable shell instructions without an intervening verification step. It is the same supply-chain exposure identified by SC2, rather than evidence of a separate malicious chaining campaign.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

bash
# macOS / Linux
curl -fsSL https://waytometa.cn/cli/install.sh | bash

# Windows PowerShell
iwr https://waytometa.cn/cli/install.ps1 -useb | iex

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

text

- 无法打开浏览器(服务器 / 容器 / 远程会话):`metadig login --no-open` 只打印链接,让用户在任何已登录设备上打开授权;仍不行时让用户设置环境变量 `METADIG_TOKEN`(值为访问令牌)或执行 `metadig login --token <令牌>`。
- 凭证存本机 `~/.metadig/credentials.json`(约 30 天有效)。命令报「尚未登录」或「登录已过期」→ 重新 `metadig login`。
- CLI 登录与用户的网页登录并存,不会把网页登录顶掉。

## 命令速查

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/cli-command-guide.md (reported line 25)May include surrounding context.

md
| 路径 | 内容 |
| --- | --- |
| `~/.metadig/credentials.json` | 登录凭证(权限 0600):`accessToken` / `userName` / `apiBase` / `savedAt`。约 30 天有效 |
| `~/.metadig/config.json` | 全局配置:`defaultProjectId`(首次生成自动创建的「CLI 项目」) |
| `<目录>/.metadig/project.json` | `metadig project use` 写的目录级项目绑定 `{ "projectId": "..." }`;从当前目录向上查找,子目录里执行命令也命中 |

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/common-pitfalls.md (reported line 64)May include surrounding context.

md
## 安全提醒

- 授权链接只在用户自己的设备上打开;别人的授权链接一律不点。
- 令牌只放环境变量或 `~/.metadig/credentials.json`,不要写进代码、日志或对话记录。
- `metadig logout` 删除本地凭证;`METADIG_TOKEN` 需另行清除。

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The troubleshooting table recommends fetching a mutable remote script and executing it directly through Bash or PowerShell. The escaped pipe is Markdown table formatting, not a security boundary; following the rendered instruction exposes the host to compromised installer code.

Content

Scanner excerpt · references/common-pitfalls.md (reported line 9)May include surrounding context.

md
| 看到 | 原因 | 怎么做 |
| --- | --- | --- |
| `metadig: command not found` / 不是内部或外部命令 | 刚装完 PATH 未刷新,或安装脚本没跑完 | 重开终端;仍不行重跑安装脚本(`curl -fsSL https://waytometa.cn/cli/install.sh \| bash` 或 PowerShell `iwr https://waytometa.cn/cli/install.ps1 -useb \| iex`),二进制装在 `~/.metadig/`(Windows `%USERPROFILE%\.metadig\`),可先用绝对路径 `~/.metadig/metadig --version` 验证 |
| `尚未登录` | 本地没有凭证且没设 `METADIG_TOKEN` | `metadig login`;无浏览器环境见下 |
| `登录已过期或无效`(401) | 凭证约 30 天过期,或 `METADIG_TOKEN` 里是旧令牌 | `metadig login` 重新授权;检查是否有过期的 `METADIG_TOKEN` 在覆盖本地凭证 |
| `令牌无效或已过期` | `--token` 给的令牌不可用,CLI 已把它清掉 | 确认令牌来源;优先走 `metadig login` 浏览器授权 |

Automatic installation executes remotely downloaded scripts without a security warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The installation workflow directs an agent to immediately execute mutable remote scripts without inspection or authenticity verification. A compromised distribution endpoint could execute arbitrary commands with the agent's operating-system permissions; HTTPS alone does not prevent this supply-chain risk.

Content

No source excerpt is available for this finding.

The troubleshooting instructions direct execution of remote installer scripts without warning about the system-integrity implications.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

Troubleshooting recommends executing remote installers again when installation or PATH resolution fails, without verifying the downloaded code. This can turn a routine diagnostic action into arbitrary code execution if the installer distribution is compromised.

Content

No source excerpt is available for this finding.

The reference-media generation workflow lacks a disclosure that local input files are uploaded for remote processing.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The workflow instructs the agent to pass a local image to the platform's video-generation service without warning that the file will be transmitted for processing. Although the guide explains that generated outputs have public URLs, it does not disclose the privacy implications of submitting reference images, videos, or audio.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.