idea2mvp@1.0.18
CAUTION· install onlyPublisher 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.
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 scenariosStatic findings
.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." 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.# 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.…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."""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.print(" 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.parser.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.**⚠️ 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..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.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."""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.ENV_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.# .env 模板Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- 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.receiver: 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.cat 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.- **`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.Cost to the agent
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%- 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.
- 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.
- 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.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.