agentic-security-audit
OfficialAudit AI agent security and trust.
Authorsparkfabrik
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Audits AI agent configurations, instruction files, and LLM integration for security risks aligned with the OWASP Top 10 for Agentic Applications (2026). It helps identify insecure patterns, review MCP/tool configurations, and enforce trust boundaries across agentic stacks.
Core Features & Use Cases
- Discover AI instruction files, MCP configurations, tool definitions, and inter-agent communication points.
- Assess integration boundaries and risk patterns, mapping findings to ASI01–ASI10 with actionable remediation guidance.
- Complement the code-security audit skill by auditing the AI-integration layer (prompts, tools, and data flows) rather than application code.
Quick Start
Provide an initial audit scope and run Phase 1 discovery to locate AI instruction files, MCP configurations, and inter-agent tools.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agentic-security-audit Download link: https://github.com/sparkfabrik/sf-awesome-copilot/archive/main.zip#agentic-security-audit Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.