Skills/ClawHub/idea2mvp

idea2mvp@1.0.18

CAUTION· install only

Publisher claims: "Discover product ideas, validate them, and build MVPs. Search trending tools across Product Hunt, GitHub, Indie Hackers, XiaoHongShu, V2EX, SSPAI, etc. Valid..." Observed in sandbox: sends data to N86T1R3OWZ-dsn.algolia.net, v.sogou.com, weixin.sogou.com, sspai.com.

Registry ClawHubPublisher morvanzhou · publishing for 262 daysInstalls 2,101Last detonated 40 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: sends data to N86T1R3OWZ-dsn.algolia.net, v.sogou.com, weixin.sogou.com, sspai.com.

Behavior trace

Honeypot run · 9 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.3snetworkCONNECT tcp://api.github.com:443
0.3sprocessexited 1: }
0.3sprocessbundled script run in the sandbox with no arguments
1.8snetworkCONNECT tcp://N86T1R3OWZ-dsn.algolia.net:443 · not in the allow-list, refused
1.8snetworkCONNECT tcp://N86T1R3OWZ-dsn.algolia.net:443 · not in the allow-list, refused
1.8snetworkCONNECT tcp://N86T1R3OWZ-dsn.algolia.net:443 · not in the allow-list, refused
1.8snetworkCONNECT tcp://N86T1R3OWZ-dsn.algolia.net:443 · not in the allow-list, refused
1.8sprocessexited 1: ❌ 未获取到任何产品
1.8sprocessbundled script run in the sandbox with no arguments
1.9sprocessexited 1: 3. 在 .skills-data/idea2mvp/.env 中写入:PRODUCTHUNT_TOKEN=your_token
1.9sprocessbundled script run in the sandbox with no arguments
6.7snetworkCONNECT tcp://v.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://v.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://v.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7snetworkCONNECT tcp://weixin.sogou.com:443 · not in the allow-list, refused
6.7sprocessexited 1: 💡 建议: 稍后重试,或减少请求频率
6.7sprocessbundled script run in the sandbox with no arguments
6.8sprocessbundled script run in the sandbox with no arguments
7.0sprocessexited 2: send_email.py: error: the following arguments are required: --subject/-s
7.0sprocessbundled script run in the sandbox with no arguments
8.7snetworkCONNECT tcp://sspai.com:443 · not in the allow-list, refused
8.7snetworkCONNECT tcp://sspai.com:443 · not in the allow-list, refused
8.7snetworkCONNECT tcp://sspai.com:443 · not in the allow-list, refused
8.7sprocessexited 1: ❌ 未获取到任何文章
8.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
8.7sprocess8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
8.7sprocessscript backend runs setup only
8.7sprocessscript backend runs setup only
8.7sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env — 配置文件(Token、搜索偏好、邮件 SMTP 等)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/producthunt_trending.py:177 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files" 3. 在 .skills-data/idea2mvp/.env 中写入:PRODUCTHUNT_TOKEN=your_token",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/send_email.py:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 指定收件人(覆盖 .env 中的默认收件人)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…技术背景、产品偏好等针对性调整搜索关键词和搜索范围。如不存在则按默认关键词执行 2. **确认搜索偏好**:检查 `.skills-data/idea2mvp/.env`,如未配置偏好则询问用户:是否配置 Product Hunt Token 以使用 API 搜索?是否使用 Playwright 控制浏览器搜索小红书?用户选择…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/utils.py:99 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""加载 .env 配置文件到环境变量(不覆盖已有环境变量)。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/send_email.py:256 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprint(" 请在 .skills-data/idea2mvp/.env 中配置邮件相关参数。", flush=True)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/send_email.py:311 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparser.add_argument("--to", help="收件人邮箱(覆盖 .env 中的 EMAIL_RECEIVER)")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files**⚠️ 凭证安全原则**:所有 Token、密码等敏感配置统一存放在 `.skills-data/idea2mvp/.env` 中,由脚本内部调用 `load_env()` 自动读取。**严禁在命令行中内联传递凭证**(如 `TOKEN=xxx python3 scripts/...`),这会导致敏感信息泄露到终端历史和日志中。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/utils.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env — 配置文件(Token、偏好、邮件等)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/send_email.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files需要环境变量(在 .skills-data/idea2mvp/.env 中配置):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/utils.py:85 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""确保 .env 文件存在,不存在则创建模板并提示用户。"""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/utils.py:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE = os.path.join(SKILL_DATA_DIR, ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/utils.py:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# .env 模板Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- 配置文件路径:`.skills-data/idea2mvp/.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/send_email.py:232 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreceiver: 收件人邮箱,为 None 时使用 .env 中的 EMAIL_RECEIVERFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/send_email.py:26 · File type combined with upload action — agent may exfiltrate local data filescat data/search-results/ph_results.txt | python3 send_email.py --subject "工具探索报告"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:131 · npx invocation of non-well-known package — may execute untrusted code- **`agent-browser`**:深入访问产品页面、社区帖子、用户评价。(如未安装,先执行:`npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser` 安装 skill).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,105 tok
1 file · 20 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

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim morvanzhou: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim morvanzhouPropose a patch to the maintainer