ai-rag-pipeline
Build Grounded RAG Research Pipelines
Research agents need current sources and clear attribution. This skill shows how to combine search, extraction, and LLM synthesis through inference.sh.
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.
Review the Skillstore skill "ai-rag-pipeline" from https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-ai-rag-pipeline/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 "ai-rag-pipeline". A user asks for a current market overview of electric vehicles.
Expected outcome:
- A research plan with Tavily and Exa searches.
- A synthesized summary of trends, risks, and open questions.
- A source list that separates cited facts from interpretation.
Using "ai-rag-pipeline". A user asks whether a public claim is supported by evidence.
Expected outcome:
- A clear claim verdict with confidence language.
- Supporting and contradicting evidence grouped by source.
- A note when evidence is weak, outdated, or incomplete.
Using "ai-rag-pipeline". A user asks to turn two URLs into an analysis brief.
Expected outcome:
- Extracted document themes and key facts.
- A concise brief with recommendations.
- Source attribution for each major claim.
Security Audit
CriticalThe audit confirms a critical pipe-to-shell installer pattern in the Quick Start and a related hardcoded installer URL. Most other static hits are Markdown formatting, illustrative infsh examples, placeholder URLs, or documentation links rather than hidden execution paths.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (66)
🌐 Network access (8)
Detected Patterns
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-ai-rag-pipeline/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-ai-rag-pipeline/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-sh-9-ai-rag-pipeline.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). ai-rag-pipeline security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline/audits/4BibTeX citation
@techreport{inference-sh-9-inference-sh-9-ai-rag-pipeline-2026,
author = {inference-sh-9},
title = {ai-rag-pipeline security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline/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: "ai-rag-pipeline security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh-9"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-9-ai-rag-pipeline/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-9-ai-rag-pipeline:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
inference-sh-ai-rag-pipeline
2026-08-21
inference-sh-9-ai-rag-pipeline
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Create Cited Research Briefs
Use search results and LLM synthesis to prepare concise briefs with source attribution.
Compare Market Signals
Gather multiple search results, identify shared themes, and surface contradictions for planning decisions.
Draft Grounded Support Answers
Retrieve current documentation or article content before generating answers for knowledge workflows.
Try These Prompts
Use the ai-rag-pipeline skill to design a simple search plus Claude answer flow for this question: [question]. Include source attribution.
Build a multi-source RAG workflow for [topic]. Search with Tavily and Exa, compare findings, and note contradictions.
Use the fact-checking pipeline to evaluate this claim: [claim]. Return a verdict, supporting evidence, conflicting evidence, and sources.
Create a reusable RAG pipeline for [domain]. Include retrieval steps, extraction, summarization strategy, citation requirements, and failure handling.
Best Practices
- Use specific queries with dates, entities, and context to improve retrieval quality.
- Ask the model to separate sourced facts from interpretation.
- Review generated citations before sharing outputs with users or teams.
Avoid
- Do not submit secrets, credentials, or private documents to external services.
- Do not treat search snippets as verified facts without source review.
- Do not run remote installer scripts without local inspection and checksum verification.
Frequently Asked Questions
Does this skill build a full vector database?
Which services does it reference?
Can it work with Claude, Codex, and Claude Code?
Does it require network access?
Can it fact-check claims?
Is it safe for confidential data?
Developer Details
Author
inference-sh-9License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
5 downloads · 128 views
File structure
📄 SKILL.md