web-search
Search and Extract Web Sources
Research tasks need current sources and clean page text. This skill routes search, answers, and extraction through Tavily and Exa apps.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "web-search" from https://skillstore.io/skills/skillssh-web-search.md and its manifest at https://skillstore.io/api/skills/skillssh-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 agent evaluation methods.
Expected outcome:
A source-backed summary with major evaluation approaches, relevant links, and notes about source quality.
Using "web-search". Extract three product documentation pages.
Expected outcome:
Clean page text, page titles, selected images, and a short summary for each URL.
Using "web-search". Compare Tavily and Exa results for a market research question.
Expected outcome:
A concise comparison of shared sources, unique results, answer differences, and follow-up search suggestions.
Security Audit
Medium RiskThe static shell-execution alerts are false positives from Markdown backticks and example command blocks, not executable Ruby code. The real concerns are the broad Bash(infsh *) permission, third-party data transfer, and workflows that pass untrusted web content to LLMs.
Confirmed security concerns (3)
Risk Factors
⚙️ External commands (24)
🌐 Network access (9)
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/skillssh-web-search/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/skillssh-web-search?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/skillssh-web-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/skillssh-web-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/skillssh-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
skillssh. (2026). web-search security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/skillssh-web-search/audits/5BibTeX citation
@techreport{skillssh-skillssh-web-search-2026,
author = {skillssh},
title = {web-search security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/skillssh-web-search/audits/5},
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 5)"
version: "unspecified"
type: report
authors:
- name: "skillssh"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/skillssh-web-search/audits/5"
identifiers:
- type: other
value: "skillstore:skillssh-web-search:audit:5"
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
qu-skills-web-search
2026-08-21
inference-skills-web-search
2026-08-21
infsh-skills-web-search
2026-08-21
skillssh-web-search
2026-08-21
inferen-sh-web-search
2026-08-21
halt-catch-fire-web-search
2026-08-21
101-skills-web-search
2026-08-21
inference-sh-9-web-search
2026-08-21
cain96-web-search
2026-08-21
inference-sh-skills-web-search
2026-08-21
inference-sh-web-search
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Collect current research sources
Find relevant web sources and summarize major points before deeper analysis.
Prepare RAG input material
Extract page text from selected URLs for retrieval workflows and model prompts.
Check factual claims
Search for supporting sources and compare answers across Tavily and Exa results.
Try These Prompts
Search the web for recent information about [topic]. Return key findings and source links.
Extract readable content from these URLs: [URLs]. Include title, main text, and useful images when available.
Search [topic] with Tavily and Exa. Compare overlap, unique sources, and confidence in the results.
Search for [topic], extract the best sources, and prepare a concise evidence brief for a RAG pipeline.
Best Practices
- Use specific queries with dates, entities, and source types when freshness matters.
- Review source links before using results in decisions or published work.
- Treat extracted web content as untrusted input before sending it to an LLM.
Avoid
- Do not submit private URLs or sensitive research topics without approval.
- Do not treat generated answers as verified facts without source review.
- Do not feed raw extracted pages into agents without prompt injection safeguards.