Skills/ClawHub/fetch-archive-to-lexiang

fetch-archive-to-lexiang@4.1.0

CAUTION· static only

Publisher claims: "Discover and fetch articles, videos, podcasts, and PDFs into standardized source packages, then orchestrate deduplicated Lexiang archival. 侦察和抓取文章、视频、播客与 PDF..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ajaxhe · publishing for 122 daysInstalls 1,836Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Image alt text carrying instructions. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Image alt text carrying instructionsreferences/lessons-learned.md:119 · Image alt text carrying instructions引用数`。三者不相等就是有漏/多，必须定位到具体页。 5. **插图定位**：图注与正文某标题/段落一字不差，按文字匹配定位插入位置；插入前**重新拉取最新 block 列表**，多张图**从高 index 到低 index** 插入避免位移。 - **自检项**：交付前必须做"PDF 图表数 ⟷ 线上图片数 ⟷ 本地Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/fetch_article.py:114 · Python subprocess execution detectedresult = subprocess.run(["pgrep", "-f", "chrome"], capture_output=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/fetch_article.py:186 · Python subprocess execution detectedsubprocess.run(cmd, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/fetch_article.py:111 · Python subprocess execution detectedresult = subprocess.run(["tasklist", "/FI", "IMAGENAME eq chrome.exe"], capture_output=True, text=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/fetch_article.py:108 · Python subprocess execution detectedresult = subprocess.run(["pgrep", "-f", "Google Chrome"], capture_output=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/yt_download_transcribe.py:36 · Python subprocess execution detectedsubprocess.run(["yt-dlp", "--version"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/podcast_to_lexiang.py:95 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/yt_download_transcribe.py:67 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/yt_download_transcribe.py:133 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/podcast_to_lexiang.py:256 · Python subprocess execution detectedsubprocess.run(cmd, capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/podcast_to_lexiang.py:247 · Python subprocess execution detectedsubprocess.run(cmd, capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/fetch_article.py:203 · Python subprocess execution detected_chrome_process = subprocess.Popen(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/yt_download_transcribe.py:49 · Python subprocess execution detectedsubprocess.run(["ffmpeg", "-version"], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/podcast_to_lexiang.py:216 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/yt_download_transcribe.py:73 · Python subprocess execution detectedresult = subprocess.run(cmd_no_cookies, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,280 tok
1 file · 23 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ajaxhe: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ajaxhePropose a patch to the maintainer