Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
Korean Scraper
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill appears to perform the advertised scraping, but it deliberately evades bot protections and runs Chromium with weakened security settings.
Install only if you are authorized to scrape the target sites and are comfortable with anti-bot evasion. Run it in an isolated environment, avoid giving it credentials or private URLs, and do not rely on the claimed robots.txt compliance unless you verify or add enforcement yourself.
Static analysis
Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
VirusTotal
66/66 vendors flagged this skill as clean.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
#
ASI02: Tool Misuse and Exploitation
High
What this means
Using this skill may violate site terms or access controls and could lead to IP blocking or other consequences for the user.
Why it was flagged
The skill openly advertises hiding automation signals, using a stealth plugin, and bypassing Cloudflare, which is beyond ordinary scraping and can be used to evade site access controls.
Skill content
**navigator.webdriver 숨김** ... **Stealth Plugin** ... **Cloudflare 우회**
Recommendation
Use only on sites where you have permission to automate access; remove or disable stealth/bypass behavior when not explicitly authorized.
#
ASI02: Tool Misuse and Exploitation
High
What this means
A malicious or compromised webpage loaded by the scraper could have a larger attack surface against the local environment or local network than it would in a hardened browser.
Why it was flagged
Every scraper creates a Chromium browser with important browser isolation protections disabled while visiting third-party pages.
Skill content
'--no-sandbox', '--disable-setuid-sandbox', '--disable-web-security', '--disable-features=IsolateOrigins,site-per-process'
Recommendation
Run the scraper in an isolated container or VM, validate target domains, and remove these browser flags unless there is a documented need.
#
ASI09: Human-Agent Trust Exploitation
Medium
What this means
Users may believe the scraper enforces site crawling rules when the reviewed code does not show that protection.
Why it was flagged
The documentation claims robots.txt compliance by default, but the provided source shows direct page navigation and rate limiting without any robots.txt fetch or enforcement logic.
Skill content
✅ robots.txt 준수 (기본값)
Recommendation
Implement actual robots.txt checking or remove the claim; users should independently verify that scraping is allowed.
#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means
Installation will fetch third-party code and browser binaries, which may change over time because versions are not fully pinned in the provided artifacts.
Why it was flagged
The skill depends on npm packages and downloads a browser runtime; this is normal for Playwright, but the provided artifacts do not include a lockfile or declared install spec.
Skill content
"install": "npx playwright install chromium" ... "playwright": "^1.41.0", "playwright-extra": "^4.3.6", "puppeteer-extra-plugin-stealth": "^2.11.2"
Recommendation
Review dependencies, use a lockfile, and install in a controlled environment.