Used Market Watch

v0.4.0

Search, brief, and monitor Korean used-market listings across 당근마켓, 번개장터, and 중고나라. Use when the user wants 중고 매물 찾아줘, 당근/번장/중고나라 동시 검색, 아이폰/맥북 같은 물건의 신규 매물...

1· 78·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match what the code implements: natural‑language parsing, Playwright-based scraping for 당근/번개/중고나라, search/brief/watch workflows, local rule storage. No unrelated credentials, services, or binaries are requested.
Instruction Scope
SKILL.md and scripts direct the agent to run the included CLI scripts and to install Playwright + Chromium. The runtime will read/write the local state file data/watch-rules.json and may launch headless Chromium to fetch public market pages. This is expected for a scraper/watch tool. No instructions attempt to read unrelated system files or export credentials; however the skill performs network scraping of external websites and will execute browser processes when run.
Install Mechanism
There is no packaged install spec in the registry entry (instruction-only). The README / SKILL.md recommend pip install playwright and python -m playwright install chromium — a normal requirement for Playwright-based code. No downloads from untrusted URLs or archive extraction are present in the bundle.
Credentials
The skill declares no required environment variables or credentials and the code does not read secrets. It only needs local filesystem access for data/watch-rules.json and to run Playwright; those are consistent with the described functionality.
Persistence & Privilege
always is false and the skill is user-invocable. It persists state only to its own data/watch-rules.json and does not modify other skills or system-wide agent settings. Autonomous invocation is allowed by platform default but not combined with unusual privileges.
Assessment
This skill appears internally consistent: it scrapes public marketplace pages using Playwright, stores watch rules/events locally in data/watch-rules.json, and emits JSON/text for cron or a higher-level messaging layer. Before installing: (1) be prepared to pip install playwright and download Chromium (the skill launches headless browsers), (2) expect scraping to be fragile (DOM changes, login/bot blocks), (3) the skill does network activity to public market sites (no hidden external endpoints or credentials requested), and (4) monitor resource use because headless browsers consume CPU/memory when run frequently. If you need integration with messaging (Telegram/Discord), you must wire that in at the OpenClaw layer — the skill deliberately does not send messages itself.

Like a lobster shell, security has layers — review code before you run it.

latestvk9794k10yb0fhpdajm3v0w2mj983jfp4

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments