Skills/ClawHub/chatgpt-ads-landing

chatgpt-ads-landing@1.0.0

CAUTION· static only

Publisher claims: "Build, deploy and verify static landing pages for ChatGPT / OpenAI Ads campaigns — any advertiser, any vertical — using the chatgpt-ads-landing engine (pages/<slug>/ + page.json → build → check → zip) and an optional compatible site-hosting platform. Covers intake of client material, page content, OpenAI Measurement Pixel events (oaiq), UTM/oppref forwarding, per-country geo routing (time zone + IP), footer privacy links, cookie consent for UK/EU, packaging, first-deploy URL backfill, and live verification (pixel really reaches OpenAI, crawlers get 200, live == build). Use this whenever someone wants to 做/改/上线/检测 an OpenAI 或 ChatGPT 广告落地页, mentions chatgpt-ads-landing, oaiq / OpenAI pixel, OAI-AdsBot, "pixel 能触发吗", "UTM 生效了吗", "是否符合 OpenAI 落地页要求", 一键部署 / 自动上线, 落地页体检, 按国家/IP 跳转, or a new client's 落地页 for ChatGPT ads — even if they don't name the skill." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher xt-felix · publishing for 0 daysInstalls 0Last detonated 10 h 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 2026-11-14 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: document.cookie access. 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
document.cookie accessscripts/verify.mjs:255 · document.cookie access — can steal session cookies…ctor('.lp-consent:not([hidden])'), consent: window.LP && LP.consent(), cookies: document.cookie.split('; ').filter(c => /^__o[pb]ref=/.test(c)).length })`; for (const c of c…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionevals/evals.json:8 · File type combined with upload action — agent may exfiltrate local data files…utput": "pages/<slug>/ created from real material only (no invented facts), page.json with US/GB sites + fallback, geo hero CTA, per-country privacy links, GB consent with cookies link, pixelEvents mapping contents_viewed/click_book/scroll…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Process kill commandscripts/lib/cdp.mjs:71 · Process kill command — agent can terminate processes// a revisit test reuses the profile. Falls back to kill after 5s.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionSKILL.md:82 · File type combined with upload action — agent may exfiltrate local data filesit in `page.json` `url` → `node scripts/package.js <slug>` (must pass) → user uploads withFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/publish.mjs:16 · File type combined with upload action — agent may exfiltrate local data files* page.json → package.js (must pass now) → upload → UpdateSite. One command replaces theFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
HTML comment carrying imperative instructions to the agentassets/starter-page/index.html:145 · HTML comment carrying imperative instructions to the agent · informational: not an instruction file有 consent 国家时,在 page.json links 里加 cookies,并在这里加一个 data-link="cookies" 的链接(href 用 link token,见 references/page-config.md)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,188 tok
1 file · 29 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

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim xt-felix: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. document.cookie access≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. File type combined with upload action≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim xt-felixPropose a patch to the maintainer