Skills/npm/guanetl

guanetl@0.1.46

VERIFIED· install only

Publisher claims: "观远 ETL 本地开发工具 - 拉取、编辑、导出、预览、保存 ETL" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher guandata · publishing for 225 daysInstalls 2,538Last detonated 46 min ago
$claude mcp add guanetl -- npx -y @guandata/guanetl
WatchReport an issue

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 0.1.45

vet-skills diff guanetl 0.1.45 0.1.46

This version reaches for something 0.1.45 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 85/100 (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 · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: If you used --omit=optional or optional=false, remove that setting first.
0.3sprocess4 of 4 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.4sprocesssecond launch, clock +45 days, CI unset

Static findings

MEDIUM
File type combined with upload actionbin/postinstall.js:33 · File type combined with upload action — agent may exfiltrate local data filesconsole.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.
AST07
MEDIUM
File type combined with upload actionskills/guanetl/SKILL.md:254 · File type combined with upload action — agent may exfiltrate local data files- `export` 后核对 `_exported.json`:每个本次需求中的输入均有对应 `INPUT_DATASET` 节点,`inputDsId` 与选定数据集一致,并沿下游 `sources` 接入预期处理/输出链。仅当用户明确要求保留未连接草稿时允许暂不接线,并标注未完成;不要强制把无关输入接到每个输出。Fix: 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 actionskills/guanetl/evals/evals.json:37 · File type combined with upload action — agent may exfiltrate local data files"避免修改 _base_etl.json、_input.json、_exported.json 等系统文件"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionskills/guanetl/SKILL.md:253 · File type combined with upload action — agent may exfiltrate local data files- 在 `BasicInputDataset` 的 `inputDsID` 参数中填写真实 ID。只列名称、只写 `meta.json.inputs`、只声明但未接入目标处理链的节点,都不能当作完成关联。Fix: 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 actionskills/guanetl/SKILL.md:178 · File type combined with upload action — agent may exfiltrate local data files`save` 会协调已保存 ETL 的输出身份:当本地 `OUTPUT_DATASET` 节点 id 变化,但它与服务端已绑定输出在同一目录、同名且双方唯一时,CLI 会自动恢复原节点 id 和 dsId,继续原地更新已有输出数据集。该协调不会修改本地 `_exported.json`,保存影响报告会显示 `save.output_binding_reconciled`。Fix: 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 actionbin/postinstall.js:50 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`[${CLI_NAME}] postinstall: AI skill updated successfully.`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagebin/run.js:177 · npx invocation of non-well-known package — may execute untrusted code// --yes: postinstall 等非交互环境下 npx 需要免确认下载 skills CLIFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionskills/guanetl/SKILL.md:465 · File type combined with upload action — agent may exfiltrate local data files| `BasicSqlScript` | 自定义 SQL | 上述节点无法满足时 | SQL 放独立 `.sql` 文件;默认上游用 `input1`/`input2`,可选工作区名称模式见下文 |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbin/postinstall.js:36 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`[${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.
AST07
HIGH
Access to sensitive file pathsbin/install-env.js:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst childEnv = { ...env };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandbin/run.js:218 · File permission modification command — agent changes file ownership/permissions// chmod may fail in read-only environmentsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈6,591 tok
1 file · 15 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for @guandata/guanetl@0.1.46 as of 11 min ago. This is the package itself, not its dependencies.