Back to skill

Security audit

aigc-web-push · AI内容生成与全网推送

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports broad activation of editing and design instructions, unpinned install commands, and a destructive draft-clearing operation; some files were only partially inspected.

Consider avoiding installation until the partially inspected scripts are reviewed and the concerns about broad activation, unpinned downloads, external data sharing, and draft deletion are addressed. The scan is incomplete, so it does not establish that the skill is safe.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Findings (25)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · Humanizer.md (reported line 170)May include surrounding context.

md
**After:**
> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
**Before:**
> The new policy — announced without warning — affects thousands of workers. The changes -- long overdue according to critics -- will take effect immediately.
**After:**
> The new policy, announced without warning, affects thousands of workers. The changes, long overdue according to critics, will take effect immediately.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · Humanizer.md (reported line 172)May include surrounding context.

md
**Before:**
> The new policy — announced without warning — affects thousands of workers. The changes -- long overdue according to critics -- will take effect immediately.
**After:**
> The new policy, announced without warning, affects thousands of workers. The changes, long overdue according to critics, will take effect immediately.

Before returning the final rewrite, scan it for `—` and `–`. Any hit means the draft isn't done. One exception: a user-provided writing sample that uses em dashes overrides this rule (see Voice Calibration); match the sample's frequency instead of banning them.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
| **check-update.js** | 同上 | 推送前核对版本;落后则暂停并提示询问用户是否升级(由 `push.js` 调用) |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 142)May include surrounding context.

md
`push.js` 推送前对照远端最新版。有新版本时**只向用户问是否升级**,并退出码 2(不自动改文件)。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 187)May include surrounding context.

md
在 **aigc-web-push 目录**执行 `push.js`;通道为 `wechat` 或 `cloud`。下方路径示例假设作品目录相对技能目录为 `../works/20261117-demo/`(按实际路径调整)。

Unconditional activation applies the humanization skill outside explicitly requested editing tasks.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The unconditional activation flag makes editorial rewriting instructions applicable beyond explicitly requested humanization tasks in hosts that honor this metadata. Rules to remove qualifications, alter structure, and inject personality could distort technical or security-sensitive output, although no malicious redirection is evident.

Content

No source excerpt is available for this finding.

Unconditional activation enables the humanizer outside explicit rewriting requests.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

Unconditional activation can introduce rewriting and output-format instructions into unrelated tasks when supported by the host. The preservation and factuality safeguards reduce the risk, but do not resolve the mismatch between global activation and a task-specific editing workflow.

Content

No source excerpt is available for this finding.

File mode overwrites the source without an advance user warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

File mode instructs the agent to replace the file's contents when the user merely points at a file, then report changes afterward. It does not require advance notice that the original prose will be overwritten or confirmation that an in-place edit is intended.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The upgrade command runs an unpinned npx package and installs a mutable remote skill revision globally. Although this is not an MCP server reference and upgrades require consent, compromised upstream releases or repository changes could introduce code or instructions with access to publishing credentials.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx remotion'.

Medium
Category
MCP Rug Pull
Confidence
82% confidence
Finding

The npx remotion instruction does not require a particular reviewed CLI version, creating a dependency-execution supply-chain risk rather than an MCP-specific issue. An existing locked local installation reduces exposure, but the instructions do not require one or prevent npx from fetching a package when local resolution fails.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This setup path executes the skills CLI without a version pin and obtains agent instructions from a mutable repository reference. An upstream compromise could therefore change both executable setup behavior and subsequent agent behavior; this is a supply-chain risk, not an MCP server configuration.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 250)May include surrounding context.

md
- 公众号 / 云电脑未指定时用 `-` → 配置里 `selected: true` 项;也可传名称或 id。
- 云电脑指定环境/账号时按名称解析,歧义则失败并打印候选。
- API 基址:`apiBase`(缺省 `https://api.pcloud.ac.cn/openAccessService`)。
- **云电脑入队即完成**:勿轮询、勿因「还没发出」重推。
- **公众号超时**:可视为已受理,勿狂推;请用户看服务通知或草稿箱。

The skill includes a draft-box clearing operation beyond its stated content-generation and publishing purpose.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

Draft cleanup is related to publishing, so its presence is not inherently a purpose violation. However, the documented bulk-clearing operation lacks an explicit user-request requirement, target preview, or destructive-action confirmation, creating a risk of deleting unrelated drafts using the configured account credentials.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 258)May include surrounding context.

清空草稿箱

POST https://api.pcloud.ac.cn/openAccessService:

json
{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · remotion-video.md (reported line 206)May include surrounding context.

md
**音乐搜索**

`GET https://api.pcloud.ac.cn/proxyService/heygen/sounds?query=%E5%85%B3%E9%94%AE%E8%AF%8D&limit=10%60

请求头(与推送相同,取自本技能目录 `config.json`):

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · config.example.json (reported line 4)May include surrounding context.

json
{
  "_fileRole": "字段说明 + 示例。正式 config.json 只保留向导输出的业务键(去掉本文件中的 _fileRole / fieldsHelp)。",
  "fieldsHelp": {
    "apiBase": "缺省 https://api.pcloud.ac.cn/openAccessService",
    "openId": "扫码得到的微信 openId;禁止编造或共用他人 config",
    "skillKey": "向导签发,与 openId 绑定;推送与音乐搜索必带;重新扫码会轮换",
    "autoUpdate": "可选;false 关闭推送前版本检查(默认开启;落后先问是否升级,不自动覆盖文件)",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · config.example.json (reported line 14)May include surrounding context.

json
},
  "version": 1,
  "description": "内容生成与全网推送(公众号 + 云电脑)",
  "apiBase": "https://api.pcloud.ac.cn/openAccessService",
  "openId": "oXXXXXXXXXXXXXXXXXXXXXXXXXXX",
  "skillKey": "请用向导扫码后生成,勿手写",
  "autoUpdate": true,

The HTML design rules activate unconditionally rather than only for HTML-generation tasks.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The unconditional flag can apply strict HTML formatting instructions to unrelated tasks in hosts that honor it. This creates an instruction-scoping and output-integrity risk, although the rules themselves concern presentation and do not request credential access or unauthorized execution.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · push-to-cloud.js (reported line 29)May include surrounding context.

js
const path = require('path');
const { URL } = require('url');

const DEFAULT_API = 'https://api.pcloud.ac.cn/openAccessService';
const DIR = __dirname;
const TARGET_SCOPES = new Set(['all', 'environment', 'account']);
const PUBLISH_MODES = new Set(['draft', 'publish', 'default']);

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · push-to-wechat-mp.js (reported line 17)May include surrounding context.

js
const path = require('path');
const { URL } = require('url');

const DEFAULT_API = 'https://api.pcloud.ac.cn/openAccessService';
const DIR = __dirname;

function readJson(name) {

The music-search workflow transmits topic-derived search terms and account information to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to derive music-search terms from the video topic and submit them with an account identifier whenever credentials are available, without a confidentiality check. For private video projects, this can disclose unreleased topics linked to a user account; authorization to publish through the provider does not necessarily authorize ancillary disclosure during production.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx remotion'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Although this is not an MCP server, npx skills can download and execute an unpinned npm package, and remotion-dev/skills identifies mutable remote skill content rather than an immutable revision. Compromise of either upstream can therefore introduce code execution or adversarial agent instructions under the user's permissions.

Content

No source excerpt is available for this finding.