📦
agent-ui
78Build React Agent Interfaces
Teams need agent chat interfaces without rebuilding streaming, approvals, and tool displays. This skill guides setup of the inference.sh Agent component in React and Next.js.
Coding & Development View
Skills web-search
📦
web-search
Content revision r1 Critical ⚙️ External commands🌐 Network access
Search Web Sources with Tavily and Exa
Research tasks need current web evidence and clean page text. This skill runs inference.sh search and extraction apps for Tavily and Exa.
Supports: Claude Codex Code(CC)
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
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/inference-sh-9-web-search.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-web-search/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.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". Find reliable sources about recent AI agent evaluation methods.
Expected outcome:
A source-backed summary with important methods, links to relevant pages, and notes on where sources disagree.
Using "web-search". Extract and summarize three product documentation pages.
Expected outcome:
A clean summary for each page, including main concepts, useful images, and any missing or inaccessible content.
Using "web-search". Research current alternatives to a search API for a RAG prototype.
Expected outcome:
A comparison of candidate services, strengths, limitations, and source links for deeper review.
Security Audit
Criticalv4 • 7/5/2026 Open versioned report
Confirmed findings are limited to the remote installer command and its pipe-to-shell execution pattern. Most static hits are Markdown fences, inline app IDs, documentation links, or bounded infsh examples, and I found no prompt injection attempt.
1
Files scanned
149
Lines analyzed
2
Review items
0
False positives ignored
Confirmed security concerns (1)
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh && infsh login
The quick start downloads a remote script with curl and pipes it directly into sh. This is a critical supply-chain execution pattern because fetched content runs before independent review.
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Ruby/shell backtick execution
```bash
This range contains a Bash quick start that runs a remote installer and starts infsh login. It is an intentional external command path, with installer execution risk covered by the blocker finding.
High
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh && infsh login
The URL is used in a command that downloads an installer from cli.inference.sh. Because the command pipes it to a shell, the network dependency has execution impact.
Risk Factors
⚙️ External commands (24)
SKILL.md:15-20 SKILL.md:20-22 SKILL.md:22-30 SKILL.md:30-31 SKILL.md:31-37 SKILL.md:37-38 SKILL.md:38-39 SKILL.md:39-45 SKILL.md:45-49 SKILL.md:49-55 SKILL.md:55-59 SKILL.md:59-65 SKILL.md:65-69 SKILL.md:69-75 SKILL.md:75-79 SKILL.md:79-85 SKILL.md:85-89 SKILL.md:89-95 SKILL.md:95-105 SKILL.md:105-109 SKILL.md:109-119 SKILL.md:119-131 SKILL.md:131-140 SKILL.md:140-142
🌐 Network access (10)
Detected Patterns
Pipe to shell pattern
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/inference-sh-9-web-search/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-sh-9-web-search?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-sh-9-web-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-web-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-sh-9-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
inference-sh-9. (2026). web-search security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-web-search/audits/4BibTeX citation
@techreport{inference-sh-9-inference-sh-9-web-search-2026,
author = {inference-sh-9},
title = {web-search security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-9-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: "inference-sh-9"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-9-web-search/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-9-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 Recommended
qu-skills-web-search
Skillstore Score 70
Evidence Confidence High
Skillstore usage 54
Updated
2026-08-21
inference-skills-web-search
Skillstore Score 70
Evidence Confidence High
Skillstore usage 12
Updated
2026-08-21
infsh-skills-web-search
Skillstore Score 68
Evidence Confidence High
Skillstore usage 9
Updated
2026-08-21
skillssh-web-search
Skillstore Score 50
Evidence Confidence High
Skillstore usage 31
Updated
2026-08-21
inferen-sh-web-search
Skillstore Score 50
Evidence Confidence High
Skillstore usage 20
Updated
2026-08-21
halt-catch-fire-web-search
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
101-skills-web-search
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
inference-sh-9 Current
inference-sh-9-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 24
Updated
2026-08-21
cain96-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 18
Updated
2026-08-21
inference-sh-skills-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
inference-sh-web-search
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance
What You Can Build
Source-backed research briefs
Gather current sources, extract key pages, and prepare a concise brief with links.
RAG source collection
Find and extract pages that can feed retrieval workflows or evaluation datasets.
Content planning research
Collect reference material, competing articles, and factual context before drafting content.
Try These Prompts
Search a Topic
Search the web for reliable sources about [topic]. Return key points, source links, and publication context.
Extract Source Material
Extract the main text from these URLs: [URLs]. Summarize each page and note images or important metadata.
Compare Search Results
Use Tavily and Exa to compare current information about [topic]. Highlight agreements, conflicts, and missing context.
Build a RAG Research Brief
Search for [question], extract the top sources, then prepare a brief with citations, uncertainty notes, and follow-up queries.
Best Practices
- Ask for source links and publication context when researching time-sensitive topics.
- Review extracted content before using it in summaries, reports, or RAG pipelines.
- Avoid sending private URLs, credentials, or confidential text to external search providers.
Avoid
- Do not treat AI-generated answers as verified facts without checking cited sources.
- Do not use the extractor on content you are not allowed to process.
- Do not pipe installer scripts to a shell without independent verification.
Frequently Asked Questions
What services does this skill use?
It uses inference.sh apps for Tavily search, Tavily extraction, Exa search, Exa answers, and Exa extraction.
Does this skill need an account?
Yes. The examples require the inference.sh CLI and an authenticated login before commands can run.
Can it browse any website?
No. Extraction depends on provider access, page availability, robots rules, and site restrictions.
Is it suitable for confidential research?
Use caution. Queries and URLs are sent to external services, so confidential material needs separate approval.
Can Claude, Codex, or Claude Code use it?
The report lists support for Claude, Codex, and Claude Code, using inference.sh command examples.
Does it replace fact checking?
No. It helps gather sources and summaries, but users must verify important claims against primary sources.
Developer Details
Author
inference-sh-9License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
23 downloads · 254 views
File structure
📄 SKILL.md
More from inference-sh-9
View all📦
tools-ui
78Add Tool Lifecycle UI to Agent Apps
Agent applications need clear tool status, approval, and result displays. This skill provides React and Next.js component guidance for those workflows.
Coding & Development View
📦
widgets-ui
77Render JSON Widgets in React
Agent output often needs interactive UI instead of plain text. This skill shows how to render structured widget definitions as React and Next.js components.
Design & Creative View
📦
chat-ui
69Build React Chat Interfaces
Teams need chat interfaces that match modern React apps. This skill provides shadcn-style components and patterns for messages, inputs, avatars, and streaming states.
Coding & Development View
📦
prompt-engineering
38Improve AI Prompts for Text, Images, and Video
AI results often fail when prompts are vague or poorly structured. This skill provides reusable patterns for LLM, image, and video prompts.
Productivity View
📦
video-prompting-guide
38Create Better AI Video Prompts
AI video prompts often fail when they miss shot, motion, lighting, or style details. This skill provides clear structures, examples, and model tips for stronger results.
Design & Creative View
Related Skills
View all📦
tavily-web
79Search and Research the Web with Tavily
by sickn33
AI assistants often need current web context and clean source material. This skill guides Tavily search, extraction, crawling, and research tasks from Claude, Codex, and Claude Code.
Research & Learning View
📦
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