Skills article-list-processor
📦

article-list-processor

Content revision r1 High Risk ⚡ Contains scripts⚙️ External commands📁 Filesystem access🔑 Env variables🌐 Network access

Process Article Lists Into Draft Posts

Collecting many article links creates slow copying and rewriting work. This skill watches a Markdown list, fetches articles, and drafts rewritten posts.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "article-list-processor" from https://skillstore.io/skills/wangdefou-dev-article-list-processor.md and its manifest at https://skillstore.io/api/skills/wangdefou-dev-article-list-processor/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/wangdefou-dev-article-list-processor.md Signed manifest GET /api/skills/wangdefou-dev-article-list-processor/manifest Signed lockfile GET /api/skills/wangdefou-dev-article-list-processor/lockfile

Test it

Using "article-list-processor". A reading list with three public article links.

Expected outcome:

  • Three draft posts are created in the output folder.
  • Each draft includes source title, source link, and generated writing sections.
  • The original list file is moved to the archive folder.

Using "article-list-processor". A list that includes one inaccessible article.

Expected outcome:

  • Reachable articles are processed normally.
  • The inaccessible article is skipped with a fetch failure message.
  • Generated drafts are still saved for successful articles.

Using "article-list-processor". A short test list while mock mode is enabled.

Expected outcome:

  • The workflow confirms link parsing and file movement.
  • Mock draft content is saved without calling the model API.
  • The archive flow can be checked before real processing.

Security Audit

High Risk
v9 • 7/7/2026 Open versioned report

I found no evidence of obfuscated malware or deliberate credential exfiltration. Confirmed risks include project .env and API key access, unrestricted outbound URL fetching, automatic file watching and reads, and an npm script execution path.

3
Files scanned
741
Lines analyzed
16
Review items
0
False positives ignored

Confirmed security concerns (6)

High
index.ts:14
Environment file access
const envPath = path.join(projectRoot, '.env');
The code builds a path to the project .env file outside the skill directory. That file is later loaded and can contain credentials, so this is real sensitive file access.
High
index.ts:25
Environment file access
const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
The line reads ANTHROPIC_API_KEY from the loaded environment. This gives the community skill runtime access to an API secret.
High
index.ts:26
Environment file access
const ANTHROPIC_BASE_URL = process.env.ANTHROPIC_BASE_URL;
The base URL setting controls where Anthropic client traffic is sent. If a hostile or mistaken value is loaded from .env, requests and possibly credentials can be redirected.
High
EVALUATION.json:15-18
Prompt Injection Attempt Detected
EVALUATION.json includes self-assessment fields that claim safe_to_publish is true and summarize the skill as low risk. This embedded self-approval can bias automated review and should not be trusted as authority.
The file does not directly command the auditor to skip review, but it asserts its own safety in machine-readable audit fields. The prompt-injection guidance flags self-approval claims as suspicious.
Medium
index.ts:119-185
Untrusted Article Content Enters LLM Prompt
Fetched article titles and body text are inserted directly into the model prompt. A malicious page can include instructions that alter generated output or weaken safety requirements.
The prompt template directly interpolates articleTitle and articleContent into the user message. There is no visible instruction boundary telling the model to treat fetched content as untrusted data.
Medium
index.ts:63-66index.ts:80-84
Unrestricted URL Fetching From Markdown Input
Any parsed link that starts with http is fetched without host validation, scheme restrictions beyond the prefix, or private-network blocking. An untrusted input list can make the runner contact internal or unwanted endpoints.
The parser accepts any link beginning with http, and fetchArticleContent passes that URL directly to fetch. I found no allowlist, DNS/IP filtering, or localhost/private address guard.
Capability review items (16)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High
index.ts:10
Node.js child_process module
import { spawn } from 'child_process';
The child_process import enables the verification routine that spawns npm later in the file. This gives the skill external command execution capability even though the command is hardcoded.
High
index.ts:198
Process spawn
const child = spawn('npm', ['run', 'skill:verify'], {
The skill runs npm run skill:verify after generating content, with shell execution enabled nearby. A package script can execute arbitrary local commands, so this is a real execution risk despite fixed arguments.
High
index.ts:25
Environment variable access (dot notation)
const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
The skill reads ANTHROPIC_API_KEY from the environment. That is expected for model access, but marketplace users must trust the skill with a live API credential.
High
index.ts:25
Environment variable object
const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
The skill reads ANTHROPIC_API_KEY from the environment. That is expected for model access, but marketplace users must trust the skill with a live API credential.
High
index.ts:23
dotenv library
dotenv.config({ path: envPath, override: true });
dotenv.config loads the project .env file with override enabled. This is sensitive because the skill runtime receives project secrets, even if it mainly uses Anthropic settings.
High
index.ts:25
Generic API/secret keys
const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
ANTHROPIC_API_KEY is read and passed into the Anthropic client. This is legitimate configuration, but it is still direct handling of a high-value API secret by community skill code.
High
index.ts:41
Generic API/secret keys
apiKey: ANTHROPIC_API_KEY || 'dummy',
ANTHROPIC_API_KEY is read and passed into the Anthropic client. This is legitimate configuration, but it is still direct handling of a high-value API secret by community skill code.
Medium
index.ts:80
Fetch API call
const response = await fetch(url, {
fetch(url) requests article links parsed from user-provided Markdown without an allowlist or private-network block. This can reach arbitrary HTTP targets from the user environment.
Medium
index.ts:6
HTTP client library
import fetch from 'node-fetch';
node-fetch is imported and used to retrieve URLs parsed from local Markdown input. This creates outbound network capability that should be reviewed for SSRF and data-flow boundaries.
Medium
index.ts:230
Node.js fs operations
const fileContent = fs.readFileSync(filePath, 'utf-8');
The skill synchronously reads filePath values delivered by the watcher. The path is expected to be under local_inputs, but there is no realpath or symlink validation before reading.
Medium
index.ts:230
Synchronous file operations
const fileContent = fs.readFileSync(filePath, 'utf-8');
The skill synchronously reads filePath values delivered by the watcher. The path is expected to be under local_inputs, but there is no realpath or symlink validation before reading.
Medium
index.ts:9
File system watching
import chokidar from 'chokidar';
The chokidar dependency is used to monitor an input directory and trigger automatic processing. The watched scope is limited, but it is still a real file observation surface.
Medium
index.ts:315
File system watching
const watcher = chokidar.watch(INPUT_DIR, {
The watcher monitors local_inputs and processes existing files because ignoreInitial is false nearby. This automatic file processing is documented, but it can surprise users if stale files are present.
Medium
index.ts:26
Environment variable access (dot notation)
const ANTHROPIC_BASE_URL = process.env.ANTHROPIC_BASE_URL;
The skill reads ANTHROPIC_BASE_URL and passes it to the SDK. A custom endpoint can redirect model traffic if the environment is misconfigured or tampered with.
Medium
index.ts:26
Environment variable object
const ANTHROPIC_BASE_URL = process.env.ANTHROPIC_BASE_URL;
The skill reads ANTHROPIC_BASE_URL and passes it to the SDK. A custom endpoint can redirect model traffic if the environment is misconfigured or tampered with.
Medium
index.ts:3
dotenv library
import dotenv from 'dotenv';
dotenv is imported and used to load project environment variables. Loading .env gives the skill access to local configuration and potential secrets.

Risk Factors

⚡ Contains scripts (5)
EVALUATION.json:18 EVALUATION.json:21 EVALUATION.json:24 EVALUATION.json:42 index.ts:63
⚙️ External commands (48)
EVALUATION.json:27 EVALUATION.json:30 EVALUATION.json:36 EVALUATION.json:18 EVALUATION.json:21 EVALUATION.json:24 EVALUATION.json:42 index.ts:10 index.ts:198 index.ts:63 index.ts:16 index.ts:79 index.ts:88 index.ts:104 index.ts:105 index.ts:113 index.ts:116 index.ts:119-177 index.ts:197 index.ts:206 index.ts:209 index.ts:222 index.ts:234 index.ts:238 index.ts:247 index.ts:252 index.ts:262 index.ts:265-274 index.ts:277 index.ts:281 index.ts:289 index.ts:291 index.ts:299 index.ts:307-313 index.ts:331 index.ts:333 index.ts:336 SKILL.md:12 SKILL.md:25 SKILL.md:27-33 SKILL.md:33-37 SKILL.md:37-39 SKILL.md:39-41 SKILL.md:41-45 SKILL.md:45 SKILL.md:50-52 SKILL.md:52-53 SKILL.md:53-55
📁 Filesystem access (25)
EVALUATION.json:54 EVALUATION.json:90 EVALUATION.json:180 EVALUATION.json:54 EVALUATION.json:186 EVALUATION.json:183 EVALUATION.json:186 EVALUATION.json:192 EVALUATION.json:168 EVALUATION.json:84 EVALUATION.json:168 index.ts:36 index.ts:230 index.ts:276 index.ts:290 index.ts:17 index.ts:36 index.ts:227 index.ts:230 index.ts:276 index.ts:13 index.ts:13 index.ts:9 index.ts:315 index.ts:329
🔑 Env variables (18)
EVALUATION.json:72 EVALUATION.json:75 EVALUATION.json:78 EVALUATION.json:171 EVALUATION.json:174 EVALUATION.json:72 EVALUATION.json:162 EVALUATION.json:339 index.ts:25 index.ts:26 index.ts:27 index.ts:25 index.ts:26 index.ts:27 index.ts:3 index.ts:23 index.ts:25 index.ts:41
🌐 Network access (6)
index.ts:80 index.ts:6 index.ts:82 SKILL.md:30 SKILL.md:31 SKILL.md:32
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/wangdefou-dev-article-list-processor/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/wangdefou-dev-article-list-processor/security.svg)](https://skillstore.io/skills/wangdefou-dev-article-list-processor?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/wangdefou-dev-article-list-processor?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/wangdefou-dev-article-list-processor/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/wangdefou-dev-article-list-processor.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

wangdefou-dev. (2026). article-list-processor security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/wangdefou-dev-article-list-processor/audits/9

BibTeX citation

@techreport{wangdefou-dev-wangdefou-dev-article-list-processor-2026, author = {wangdefou-dev}, title = {article-list-processor security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/wangdefou-dev-article-list-processor/audits/9}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "article-list-processor security audit report (audit version 9)" version: "unspecified" type: report authors: - name: "wangdefou-dev" date-released: "2026-07-07" url: "https://skillstore.io/skills/wangdefou-dev-article-list-processor/audits/9" identifiers: - type: other value: "skillstore:wangdefou-dev-article-list-processor:audit:9" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
85
Content
70
Community
83
Spec Compliance

What You Can Build

Draft posts from saved reading links

Convert a reading list into draft posts for review and editing.

Process source links in batches

Turn multiple source articles into candidate summaries or rewrites.

Prepare article-based social drafts

Create first-pass posts from public articles for later approval.

Try These Prompts

Process One List 
Process my Markdown reading list and save one draft for each valid article link.
Test With Mock Mode 
Run the article list workflow in mock mode and confirm that each link is detected correctly.
Review Generated Drafts 
Summarize the generated drafts and flag items that need source review before publishing.
Run A Guarded Batch 
Process only approved public article links, skip blocked domains, and keep source attribution in every draft.

Best Practices

  • Use only public article URLs that you are allowed to fetch.
  • Run mock mode first to confirm the input file format.
  • Review every generated draft for accuracy, attribution, and policy compliance.

Avoid

  • Do not process private, login-only, or confidential links.
  • Do not publish generated text without human review.
  • Do not run the watcher in a project with unrelated sensitive input files.

Frequently Asked Questions

What input format does it expect?
It expects Markdown or text files containing article links in title and URL format.
Where are generated drafts saved?
Drafts are written under the configured project output folder for Defou Stanley posts.
Does it need network access?
Yes. It fetches article pages and sends prompts to the configured Anthropic API endpoint.
Can it run without an API key?
Mock mode can test the file workflow, but real generation requires an Anthropic API key.
Does it change input files?
Yes. After processing, it moves each input list into an archive folder.
Is the generated content ready to publish?
No. The output is a draft and should be reviewed for accuracy, originality, and permissions.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/wangdefou-dev/defou-workflow-agent/tree/main/skills/article-list-processor

Ref

36e07d5e13068e5be64447e8f20b427cf2cbd21a

Maintenance freshness

7/18/2026

Usage

16 downloads · 206 views

File structure

📄 EVALUATION.json

📄 index.ts

📄 SKILL.md