Skip to content
TrustedSkillsbeta
Back to all skills

Clawscan

Listed
osmankidwai-bot·vlatest·writing·MIT

Clawscan identifies potential vulnerabilities in code by simulating attacks and analyzing system behavior for suspicious activity, boosting security.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add osmankidwai-bot/clawscan --skill clawscan -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

osmankidwai-bot

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 7 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: buy.stripe.com, feross.org, opencollective.com, paulmillr.com, tidelift.com….

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    github.comsource hostraw.githubusercontent.comsource hostbuy.stripe.comundeclaredtwitter.comundeclaredopencollective.comundeclaredtidelift.comundeclaredpaulmillr.comundeclaredwww.patreon.comundeclaredfeross.orgundeclared

    What it found (3 of 25)

    • site/app/page.tsx:300contacts buy.stripe.com
      href="https://buy.stripe.com/test_3cIaEX4fI8MO2kC9uWcQU00"
    • site/app/page.tsx:332contacts buy.stripe.com
      href="https://buy.stripe.com/test_7sYbJ1cMe9QS1gy6iKcQU01"
    • site/app/page.tsx:346contacts buy.stripe.com
      <a href="https://buy.stripe.com/test_9B69AT6nQ1km0cubD4cQU02" className="inline-flex items-center justify-center px-6 py-3 border border-accent/40 text-accent …

  • No credential access: failed

    Touches credential material in 10 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found (3 of 10)

    • clawscan.py:69SSH private keys or config
      os.path.expanduser("~/.ssh"),
    • clawscan.py:197SSH private keys or config
      r"/etc/(passwd|shadow|sudoers|hosts)|/root/|~/.ssh/",
    • security-checks.json:191SSH private keys or config
      "\\.ssh/id_rsa",

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned osmankidwai-bot/clawscan at e5eacda970.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
e5eacda970
Manifest
SKILL.md
Scanned
22 files, 4,514 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The clawscan skill provides a way to scan and extract data from web pages. It can be used to identify elements on a page, retrieve specific text content, or gather structured information based on defined patterns. This allows AI agents to interact with websites in a more targeted and efficient manner than simple browsing.

When to use it

  • Data Extraction: Automatically pull product details (price, description) from an e-commerce website for price comparison.
  • Content Summarization: Extract key paragraphs or sections from a news article to generate a concise summary.
  • Web Scraping: Gather data points like contact information or event listings from various web pages.
  • Form Filling: Automatically populate fields in online forms by extracting data from related documents or websites.

Key capabilities

  • Web page scanning
  • Element identification
  • Text content retrieval
  • Structured data extraction

Example prompts

  • "Scan this webpage [URL] and extract the product price."
  • "From this URL [URL], find all instances of email addresses."
  • "Can you scan this page [URL] and summarize the main points in three sentences?"

Tips & gotchas

The skill's effectiveness depends on the structure and consistency of the target web pages. Complex or dynamically generated websites may require more specific instructions for accurate data extraction.