📦
ai-image-generation
69Generate AI Images with Hosted Models
Creating model-specific image commands can be slow and inconsistent. This skill provides belt CLI examples for generation, editing, stitching, and upscaling.
Design & Creative View
Skills web-search
📦
web-search
Content revision r1 Medium Risk ⚙️ External commands🌐 Network access
Search and Extract Web Research
Research tasks need current sources and clean page text. This skill routes Claude, Codex, and Claude Code requests through Tavily and Exa using the belt CLI.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "web-search" from https://skillstore.io/skills/qu-skills-web-search.md and its manifest at https://skillstore.io/api/skills/qu-skills-web-search/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "web-search". Search for recent research on battery recycling policy.
Expected outcome:
A concise source list with current policy coverage, short notes, and recommended next searches.
Using "web-search". Extract this long article and summarize the key claims.
Expected outcome:
Clean article text, a short claim summary, source details, and important caveats.
Using "web-search". Compare Tavily and Exa results for an emerging market.
Expected outcome:
A ranked source comparison showing overlap, gaps, and sources worth reviewing first.
Security Audit
Medium Riskv4 • 7/5/2026 Open versioned report
The static external-command findings are Markdown inline code or fenced examples, not Ruby backtick execution in runnable skill code. The remaining real risks come from broad belt CLI permission and expected transfer of queries, URLs, and extracted content to third-party services.
1
Files scanned
153
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Broad Belt CLI Permission
The front matter permits Bash(belt *), which allows any belt subcommand instead of only the listed Tavily and Exa apps. This can run unrelated network-capable apps or account commands if prompt context is misused.
The allowed-tools line directly grants a wildcard belt command scope. The file later documents only a small subset of intended apps, so the permission is broader than needed.
Medium
External Data Transfer by Design
The examples send user queries, URLs, and extracted content to Tavily, Exa, OpenRouter, and inference.sh services. This is expected for the tool, but private data can leave the local environment.
The documented belt app runs include search queries, extraction URLs, and LLM prompts. These commands clearly use external services, though that is the intended capability.
Risk Factors
⚙️ External commands (25)
SKILL.md:7 SKILL.md:17 SKILL.md:19-24 SKILL.md:24-33 SKILL.md:33-34 SKILL.md:34-40 SKILL.md:40-41 SKILL.md:41-42 SKILL.md:42-48 SKILL.md:48-52 SKILL.md:52-58 SKILL.md:58-62 SKILL.md:62-68 SKILL.md:68-72 SKILL.md:72-78 SKILL.md:78-82 SKILL.md:82-88 SKILL.md:88-92 SKILL.md:92-98 SKILL.md:98-108 SKILL.md:108-112 SKILL.md:112-122 SKILL.md:122-134 SKILL.md:134-143 SKILL.md:143-145
🌐 Network access (9)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/qu-skills-web-search/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/qu-skills-web-search?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/qu-skills-web-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/qu-skills-web-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/qu-skills-web-search.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
qu-skills. (2026). web-search security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/qu-skills-web-search/audits/4BibTeX citation
@techreport{qu-skills-qu-skills-web-search-2026,
author = {qu-skills},
title = {web-search security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/qu-skills-web-search/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "web-search security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "qu-skills"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/qu-skills-web-search/audits/4"
identifiers:
- type: other
value: "skillstore:qu-skills-web-search:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
11 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
qu-skills-web-search
Skillstore Score 70
Evidence Confidence High
Skillstore usage 56
Updated
2026-09-09
inference-skills-web-search
Skillstore Score 70
Evidence Confidence High
Skillstore usage 13
Updated
2026-09-09
infsh-skills-web-search
Skillstore Score 68
Evidence Confidence High
Skillstore usage 9
Updated
2026-09-09
skillssh-web-search
Skillstore Score 50
Evidence Confidence High
Skillstore usage 33
Updated
2026-09-09
inferen-sh-web-search
Skillstore Score 50
Evidence Confidence High
Skillstore usage 21
Updated
2026-09-09
101-skills-web-search
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-09-09
halt-catch-fire-web-search
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-09-09
inference-sh-9-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 25
Updated
2026-09-09
cain96-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 20
Updated
2026-09-09
inference-sh-skills-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-09-09
inference-sh-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
85
Content
73
Community
91
Spec Compliance
What You Can Build
Prepare Current Briefings
Gather current source links and summaries before writing a briefing or report.
Collect RAG Inputs
Extract clean web page text before adding material to a retrieval workflow.
Check Published Claims
Search independent sources and compare answers before relying on a public claim.
Try These Prompts
Basic Search
Search the web for [topic] and return the most useful sources with short notes.
Extract Article Details
Extract readable content from [URL] and summarize the main claims, evidence, and author context.
Compare Sources
Search Tavily and Exa for [topic], compare source agreement, and flag outdated or weak evidence.
Build Research Workflow
Run a search on [topic], extract the top relevant pages, then prepare a sourced briefing with open questions.
Best Practices
- Use focused queries with dates, named entities, and clear scope.
- Review source URLs before relying on generated answers.
- Keep private or regulated content out of search and extraction requests.
Avoid
- Sending secrets, credentials, or confidential documents to external search tools.
- Treating direct answers as final facts without checking sources.
- Running broad belt commands that are unrelated to the listed search apps.
Frequently Asked Questions
Does this skill need an external account?
Yes. It requires the inference.sh belt CLI and any needed authentication for the connected apps.
Which search providers does it use?
The documented examples use Tavily and Exa through the inference.sh belt CLI.
Can it extract content from any URL?
It can request extraction, but access depends on the provider, page rules, and source availability.
Is private content safe to send?
Do not send private, regulated, or secret content unless your policies allow those external services.
Does it verify facts automatically?
No. It returns search and extraction results that should be checked against trusted sources.
Can Claude Code or Codex use it?
Yes. The report lists Claude, Codex, and Claude Code as supported tools.
Developer Details
Author
qu-skillsLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
52 downloads · 0 views
File structure
📄 SKILL.md
More from qu-skills
View all📦
ai-video-generation
68Create AI Videos with Inference.sh Models
Creating video workflows across many AI models can be slow and confusing. This skill organizes inference.sh model choices and belt CLI steps for video generation, animation, editing, and utilities.
Design & Creative View
📦
remotion-render
50Render Remotion Videos from TSX
Creating MP4 videos from React animations can require local setup and render infrastructure. This skill routes Remotion TSX through inference.sh and returns a rendered video.
Design & Creative View
📦
ai-avatar-video
50Create AI Avatar Videos With CLI Workflows
AI avatar video creation often requires choosing models, voices, audio, and CLI options. This skill provides ready workflows for talking heads, dubbing, and UGC-style presenters.
Design & Creative View
📦
twitter-automation
50Automate Twitter and X Workflows
Social teams need reliable X actions without rewriting command syntax. This skill turns common Twitter/X tasks into guided belt CLI workflows.
Communication View
📦
python-executor
38Run Python Tasks in a Hosted Sandbox
Many agent workflows need Python for data, media, and automation tasks without local setup. This skill routes Python code to a hosted inference.sh environment with common libraries preinstalled.
Coding & Development View
Related Skills
View all📦
tavily-search
79Search the Web with Tavily
by CK991357
AI assistants often lack current information for news, prices, releases, and fast-moving topics. This skill guides Claude, Codex, and Claude Code to call Tavily Search with clear query parameters.
Research & Learning View
📦
firecrawl-search
78Search the Web with Firecrawl
by firecrawl
Current web research often needs more than short search snippets. This skill runs Firecrawl searches, saves structured results, and can extract full page content for review.
Research & Learning View
📦
exa-search
78Search the Web Semantically with Exa
by sickn33
Keyword searches can miss conceptually relevant sources and related content. This skill guides Exa API searches for semantic discovery, category filtering, and structured research.
Research & Learning View
📦
nature-reviewer
81Simulate Nature-Style Reviewer Reports
by Yuan1z0825
Researchers often need an objective pre-submission critique before sending a manuscript. This skill turns supplied manuscript material into grounded Nature-style reviewer reports.
Research & Learning View
📦
deep-research
80Research Complex Topics With Citations
by shubhamsaboo
Deep research is hard when sources disagree or lack context. This skill guides Claude, Codex, and Claude Code to synthesize sources, compare viewpoints, and produce cited research summaries.
Research & Learning View
📦
technical-research
79Evaluate Technical Options with Structured Spikes
by 89jobrien
Technical decisions often need evidence, not opinion. This skill guides timeboxed spikes with options, proof of concept results, comparison matrices, risks, and recommendations.
Research & Learning View