Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Amazon Search
v0.1.1Search Amazon product listings for a keyword and return structured JSON results. Results are cached by ASIN/uuid for incremental searches and saved automatic...
⭐ 0· 19·0 current·0 all-time
byWei Han@mikehankk
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Amazon search + caching + image download) matches the included files: Playwright search/get-cookie scripts, a coordinator script (amazon_search.ts), and an image-cache module. Required tools (Playwright, Node/Bun) are consistent with scraping and image handling.
Instruction Scope
Instructions stay within the stated purpose: they tell the agent/user how to run the Playwright-based search, manage cache, and download images. Notable behaviours the user should expect: the Playwright scripts capture cookies, save debug_screenshot.png and debug_page.html, and persist session JSON files (cookies and UA) under cache/sessions and search caches under resultscache/results. These are expected for a scraper but are sensitive (contain cookies and saved HTML).
Install Mechanism
No formal registry install spec (instruction-only), but SKILL.md asks the user to install Bun via a curl | bash installer and to run npm install + npx playwright install chromium. Those are expected for this skill, but running remote install scripts (curl https://bun.sh/install | bash) and Playwright's browser downloads carry the usual supply-chain/network risks and should be done from a trusted environment.
Credentials
The skill does not request secrets or credentials. It documents two optional env vars (T2P_PROXY and T2P_IMAGE_DIR) which the code uses. No unrelated credentials, config paths, or unexpected env variables are requested.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It persists only its own data (sessions, caches, results, debug files) under the project directory; this is consistent with its purpose and does not modify other skills or global agent configs.
Assessment
This skill appears to do what it says: headless Playwright scraping of Amazon with local caching and optional image download. Before installing, consider: (1) the scripts will save Amazon cookies, HTML snapshots, screenshots, session JSON and cached images to the local project folders (resultscache, cache/sessions, results, debug files) — these can contain sensitive data; (2) SKILL.md recommends running a remote Bun install script (curl | bash) and Playwright will download browser binaries — perform these steps only on trusted machines or isolated environments; (3) the skill supports a proxy via T2P_PROXY — be cautious about pointing it at third-party proxies (they could see scraped traffic and cookies); (4) if you want to limit persistence, run in a disposable container and clear the resultscache/cache/sessions/results directories after use. If you need higher assurance, review the included files locally and/or run them in an isolated environment (container/VM) before granting broader access.scripts/amazon_search.ts:16
Shell command execution detected (child_process).
scripts/vendors/image-cache/src/index.ts:17
Environment variable access combined with network send.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk974h98dmp8tg29qm36mb7p55x84bpb6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.