skills.rest
maruakshay
maruakshayCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

crewai-agent-security

Audit CrewAI agent systems for role-boundary violations and prompt-injection risks.

4|Updated Apr 27, 2026
Search Tags:#multi-agent#auditing#crewai#access-control#prompt-injection#agent-security
One-click install
npx skills add https://github.com/maruakshay/mii-ai-security --skill crewai-agent-security
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: crewai-agent-security
Source: https://github.com/maruakshay/mii-ai-security/tree/main/skills/crewai-agent-security
Command: npx skills add https://github.com/maruakshay/mii-ai-security --skill crewai-agent-security

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

CrewAI agent systems are vulnerable to role boundary violations, task delegation abuse, and shared-context poisoning, which can enable prompt injection and tool misuse.

Core Features & Use Cases

  • Per-agent tool scoping enforces tools are bound to each agent's role to prevent cross-agent escalation.
  • Context isolation and sanitization prevents leakage and instruction injection by stripping sensitive data before sharing outputs.
  • Audit and logging of delegation, tool calls, and shared-context changes for post-incident analysis.
  • Use cases include evaluating a CrewAI workflow for role adherence, validating tool permissions, and hardening agent collaborations in complex tasks.

Quick Start

Audit your CrewAI setup by listing each agent and confirming its allowed tools.

Frequently Asked Questions about crewai-agent-security

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent prompt injection in CrewAI multi-agent systems?▼

Prevent prompt injection in CrewAI by applying per-agent tool scoping, context isolation, and output sanitization to stop instruction injection and context poisoning across shared task descriptions.

What's the best way to enforce tool access control for CrewAI agents?▼

Enforce tool access control for CrewAI agents by binding tools directly to each agent's role, preventing cross-agent escalation and task delegation abuse in hierarchical workflows.

How do I audit role boundary violations in CrewAI agent workflows?▼

Audit role boundary violations in CrewAI by logging delegation events, tool calls, and shared-context changes to generate auditable records for post-incident security analysis.

Does CrewAI support context isolation between agents in shared workflows?▼

CrewAI shared-context poisoning is mitigated by stripping sensitive data before sharing outputs, isolating context between agents to prevent leakage and instruction injection in collaborative tasks.

Why does my CrewAI agent have access to tools outside its role?▼

CrewAI agents gain unauthorized tool access when per-agent tool registration is not enforced, allowing cross-agent escalation; binding tools to each agent's role prevents this security gap.

When do I need security auditing for multi-agent CrewAI workflows?▼

Security auditing for multi-agent CrewAI workflows is needed when agents share task descriptions, call tools collaboratively, or operate in hierarchical structures vulnerable to context poisoning and role abuse.

Related Skills

Explore More Software Engineering Skills→
giosuetedeschi-specgiosuetedeschi-spec

crewai

Orchestrate multi-agent teams with roles, tasks, and sequential or hierarchical workflows.

Community
Advanced
claude-office-skillsclaude-office-skills
368

Security Monitoring

Automate security monitoring, threat detection, and incident response workflows.

Official
Advanced
williamzujkowskiwilliamzujkowski
17

authorization-security

Implement RBAC and ABAC authorization with policy enforcement and audit trails.

Community
Advanced
xurenluxurenlu
1

agent-governance

Implement governance controls for AI agents with declarative policies and audit trails.

Community
Advanced