Skills/npm/atlas-loop

atlas-loop@0.1.10

CAUTION· install only

Publisher claims: "Atlas Loop —— 通用的递归学习地图 Agent Skill:把任何陌生主题拆解为独立离线的交互式 HTML 地图,并为每个节点配上深入探究与递归子图提示。" Observed in sandbox: calls registry.npmjs.org only, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher liduchuan · publishing for 6 daysInstalls 1,825Last detonated 58 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
7 of 7 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 0.1.8

vet-skills diff atlas-loop 0.1.8 0.1.10

This version reaches for something 0.1.8 did not: 1 new host (registry.npmjs.org). Compared from the two recorded runs, not from source.

New hosts
registry.npmjs.org

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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 72/100 (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: calls registry.npmjs.org only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 23 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: 用法:node build_atlas.mjs --data <graph-data.json> [--out <output.html>]
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: 用法:node profile.mjs <read|record|list> [选项]
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: 用法:node verify_atlas.mjs --html <atlas.html 的路径>
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments
7.2sfilesystemread ~ · ~/work · ~/work/acme-api outside project
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2snetworkCONNECT tcp://registry.npmjs.org:443
7.2sprocessexec /usr/local/bin/npm
7.2sprocessexec /tmp/ks-detonate-J8o62H/scripts/home/work/acme-api/.claude/skills/atlas-loop/node_modules/esbuild/bin/esbuild
7.2sprocessexec /tmp/ks-detonate-J8o62H/scripts/home/work/acme-api/.claude/skills/atlas-loop/node_modules/@esbuild/linux-x64/bin/esbuild
7.2sprocessbundled script run in the sandbox with no arguments
22sfilesystemread ~ · ~/work · ~/work/acme-api outside project
22sprocessexec /tmp/ks-detonate-J8o62H/scripts/home/work/acme-api/.claude/skills/atlas-loop/node_modules/@esbuild/linux-x64/bin/esbuild
22sprocess7 of 7 bundled scripts run with no arguments
22sprocessscript backend runs setup only
22sprocessscript backend runs setup only
22sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionbin/atlas-loop.mjs:26 · File type combined with upload action — agent may exfiltrate local data filesnpx @liduchuan/atlas-loop build --data <graph-data.json> [--out <output.html>]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 pathstemplate/build-shell.mjs:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.replace(/import\.meta\.env/g, '({MODE:"production"})')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebin/atlas-loop.mjs:24 · npx invocation of non-well-known package — may execute untrusted codenpx @liduchuan/atlas-loop install [--dir <skills-dir>]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathstemplate/dev-server.mjs:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn res.outputFiles[0].text.replace(/import\.meta\.env/g, '({MODE:"development"})');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 pathstemplate/dev-server.mjs:54 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn fs.readFileSync(tmpOut, 'utf8').replace(/import\.meta\.env/g, '({MODE:"development"})');Fix: 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/build_atlas.mjs:296 · File type combined with upload action — agent may exfiltrate local data filesconsole.error('用法:node build_atlas.mjs --data <graph-data.json> [--out <output.html>]');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 actionSKILL.md:102 · File type combined with upload action — agent may exfiltrate local data filesnode <skill_dir>/scripts/build_atlas.mjs --data /tmp/atlas-loop-<ts>/graph-data.json --out <output_html>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/atlas-loop.mjs:25 · npx invocation of non-well-known package — may execute untrusted codenpx @liduchuan/atlas-loop dev [--port 5179] [--data <graph-data.json>]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/atlas-loop.mjs:27 · npx invocation of non-well-known package — may execute untrusted codenpx @liduchuan/atlas-loop verify --html <output.html>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/atlas-loop.mjs:26 · npx invocation of non-well-known package — may execute untrusted codenpx @liduchuan/atlas-loop build --data <graph-data.json> [--out <output.html>]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,662 tok
1 file · 18 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 @liduchuan/atlas-loop@0.1.10 as of 7 min ago. This is the package itself, not its dependencies.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim liduchuan: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  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. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. 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.
  6. 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 npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim liduchuanPropose a patch to the maintainer