Skills/ClawHub/local-rag-builder

local-rag-builder@1.6.0

CAUTION· static only

Publisher claims: "本地 RAG 系统搭建技能，支持环境检测修复、嵌入模型多源下载、5种切分策略 + GuardStack + 后处理 + 插件注册、多知识库管理 + 自动分类规则、可调 Prompt、Web 可视化配置 + 极客模式 + 模板管理" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ldxs001 · publishing for 142 daysInstalls 1,309Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python subprocess execution detectedscripts/rag_env_setup.py:168 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rag_env_setup.py:409 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rag_env_setup.py:235 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Unicode escape sequence detectedscripts/rag_web_ui.py:629 · Unicode escape sequence detected — may contain obfuscated payloadsvar name = prompt('\u8f93\u5165\u6a21\u677f\u540d\u79f0\uff08\u4f8b\u5982\uff1a\u201c\u6211\u7684\u6280\u672f\u6587\u6863\u914d\u7f6e\u201d\uff09:');Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedscripts/rag_env_setup.py:475 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Unicode escape sequence detectedscripts/rag_web_ui.py:481 · Unicode escape sequence detected — may contain obfuscated payloads<button class="btn btn-danger" onclick="if(confirm('\u786e\u5b9a\u91cd\u7f6e\u6240\u6709\u914d\u7f6e\uff1f'))resetAll()">&#x1f5d1;&#xfe0f; \u91cd\u7f6e\u914d\u7f6e</button>Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedscripts/rag_env_setup.py:180 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/utils.py:54 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Unicode escape sequence detectedscripts/rag_web_ui.py:637 · Unicode escape sequence detected — may contain obfuscated payloadsif(d.success) {{ toast('\u6a21\u677f\u5df2\u4fdd\u5b58\uff1a'+name); refreshGeekTemplates(); }}Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedscripts/utils.py:91 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Unicode escape sequence detectedscripts/rag_web_ui.py:631 · Unicode escape sequence detected — may contain obfuscated payloadsvar label = prompt('\u8f93\u5165\u6a21\u677f\u63cf\u8ff0\uff08\u53ef\u7a7a\uff09:') || name;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detectedscripts/rag_web_ui.py:643 · Unicode escape sequence detected — may contain obfuscated payloadsif(!confirm('\u786e\u5b9a\u52a0\u8f7d\u6a21\u677f "'+name+'" \u5e76\u8986\u76d6\u5f53\u524d\u914d\u7f6e\uff1f')) return;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈1,781 tok
1 file · 21 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

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ldxs001: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ldxs001Propose a patch to the maintainer