guancli@1.0.73
VERIFIED· install onlyPublisher claims: "观远 BI 命令行工具 - 通过 API 操作 ETL、数据集、页面、表单等资源,并提供 ChatBI 问数/洞察能力" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 4 of 4 bundled scripts run with no arguments, 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
What changed since 1.0.72
vet-skills diff guancli 1.0.72 1.0.73This version reaches for something 1.0.72 did not: 1 new install script (node bin/postinstall.js). Compared from the two recorded runs, not from source.
- New install scripts
- node bin/postinstall.js
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 3 scenarios · 0 deviationsStatic findings
console.log(`[${CLI_NAME}] postinstall: AI skill updated successfully.`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- 该命令会下载 SuperApp 模板并创建项目目录,随后尝试复制 `.env.template`、更新 `package.json` 名称、初始化 git,并根据模板情况执行 `setup.sh` 或 `npm install` + 启动本地 dev server。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(`[${CLI_NAME}] postinstall: refreshing AI skill (${CLI_NAME} install-skill)...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const childEnv = { ...env };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(`[${CLI_NAME}] postinstall: skipping automatic install-skill (${reason}).`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.// --yes: postinstall 等非交互环境下 npx 需要免确认下载 skills CLIFix: Pin versions and sources; vendor anything fetched at install time.| 仅改提示词或本次筛选条件(仪表板须已开启洞察) | `config preview --config-file insight.json --output preview-result.json`,检查结果后按用户目标决定是否保存;预览不写配置 |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.| 按已保存配置生成报告 | `insight page <page_id> --output result.json`;卡片用 `insight card <cd_id> --page-id <page_id> --output result.json`。使用 BI 已保存配置,不读取本地配置文件;`--selector` 仅影响本次筛选条件。等待同一次执行结束并检查结果 |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.// chmod may fail in read-only environmentsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.| 预览本地配置中的提示词 | `insight config preview --config-file insight.json --output preview-result.json`,同时支持 PAGE 和 CARD;使用文件中的提示词及本次筛选条件,不保存配置 |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
Not checked against OSV yet; the weekly check has not reached this version.