Skills crewai
📦

crewai

Content revision r2 High Risk ⚙️ External commands

Design Reliable CrewAI Agent Teams

Multi-agent projects often fail because roles, tasks, dependencies, and control flow are unclear. This skill provides practical CrewAI patterns for structured Python workflows.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "crewai" from https://skillstore.io/skills/sickn33-crewai.md and its manifest at https://skillstore.io/api/skills/sickn33-crewai/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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 "crewai". Design a crew that researches a market and produces an executive brief.

Expected outcome:

  • Research agent: gathers cited market evidence from approved sources.
  • Analyst agent: compares trends, competitors, and uncertainties.
  • Writer agent: produces the brief from reviewed research and analysis.
  • Process: sequential, with explicit expected outputs and a review gate.

Using "crewai". Should a support-triage crew use sequential or hierarchical execution?

Expected outcome:

Use hierarchical execution when a manager must assign cases by specialty and resolve conflicts. Use sequential execution for a fixed classify, investigate, and respond pipeline.

Using "crewai". Review a CrewAI workflow that gives every agent every tool.

Expected outcome:

  • Primary risk: excessive tool access increases the effect of mistakes and prompt injection.
  • Recommendation: assign only task-specific tools and require approval for sensitive actions.
  • Validation: test denied operations, malformed inputs, timeouts, and partial failures.

Security Audit

High Risk
v5 • 7/23/2026 Open versioned report

All seven static command findings are false positives caused by Markdown fences or inline code, with no Ruby or shell execution present. Semantic review identified unrestricted agent-controlled SQL execution and untrusted web research flowing into a downstream agent. Add database controls and indirect prompt injection defenses before publication.

1
Files scanned
459
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (2)

High
Unrestricted Agent-Controlled SQL Execution
The custom tool passes arbitrary SQL directly to db.execute and assigns the tool to an agent. Model-generated or injected SQL could expose, alter, or delete data.
The example directly connects an unrestricted SQL string to database execution and exposes that function as an agent tool. No validation, authorization, or read-only boundary is shown.
Medium
Untrusted Web Content Reaches a Downstream Agent
The research agent uses web tools, and its output becomes writing-task context without isolation or validation. Malicious pages could influence downstream instructions through indirect prompt injection.
The configuration explicitly combines web retrieval with downstream task context. The absence of a trust-boundary control is clear, although exploit impact depends on the deployed tools and prompts.
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.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-crewai/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-crewai/security.svg)](https://skillstore.io/skills/sickn33-crewai?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-crewai?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-crewai/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-crewai.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

sickn33. (2026). crewai security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-crewai/audits/5

BibTeX citation

@techreport{sickn33-sickn33-crewai-2026, author = {sickn33}, title = {crewai security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/sickn33-crewai/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: "crewai security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-23" url: "https://skillstore.io/skills/sickn33-crewai/audits/5" identifiers: - type: other value: "skillstore:sickn33-crewai:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Build a Research and Writing Crew

Design agents, tasks, and context dependencies for a repeatable research-to-content workflow.

Choose an Orchestration Process

Compare sequential and hierarchical processes for a multi-agent workload with clear delegation needs.

Plan a Stateful Agent Workflow

Map events, routers, memory, and specialized crews into a controlled CrewAI Flow.

Try These Prompts

Create a Basic Crew
Design a minimal CrewAI team for [goal]. Define each agent, task, expected output, and execution order. Explain the choices.
Structure YAML Configuration
Convert this workflow into CrewAI agent and task configuration: [workflow]. Include roles, goals, dependencies, inputs, and expected outputs.
Select the Process Model
Assess this multi-agent workflow: [details]. Recommend sequential or hierarchical execution. Identify delegation boundaries, dependencies, and failure points.
Design a Production Flow
Design a CrewAI Flow for [system]. Include state, routing, memory, approval gates, tool permissions, error handling, observability, and test criteria.

Best Practices

  • Give every agent one clear responsibility and measurable expected outputs.
  • Use least-privilege tools, validated inputs, and approval gates for sensitive actions.
  • Test task dependencies, routing, memory behavior, retries, and partial failures.

Avoid

  • Do not create many agents when a deterministic function or single model call is sufficient.
  • Do not pass untrusted retrieved content into agent instructions without isolation and validation.
  • Do not expose unrestricted database, filesystem, or network tools to autonomous agents.

Frequently Asked Questions

What does this skill help me build?
It helps design CrewAI agents, tasks, crews, tools, memory, planning, and event-driven flows.
Does it install or run CrewAI?
No. It provides design and implementation guidance for a Python environment that you manage.
When should I use a sequential process?
Use sequential execution when tasks follow a stable order and each output feeds the next task.
When should I use a hierarchical process?
Use hierarchical execution when a manager must delegate dynamic work among specialized agents.
Does it cover persistent workflows?
Yes. It describes memory configuration and CrewAI Flows with state, listeners, and routing.
What production safeguards are still required?
Add authorization, input validation, least-privilege tools, approval gates, observability, error handling, and tests.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

f9e2c34b4f19c7f3e6b0a1e93227b5f77cc12526

Maintenance freshness

7/26/2026

Usage

6 downloads · 102 views

File structure

📄 SKILL.md