mcpField
A
agentic-ai-risk-assess

agentic-ai-risk-assess

github.com/owaspSecurity208133 installsUpdated 2w ago
Repository

About agentic-ai-risk-assess

This skill guides security reviewers through risk assessments of agentic AI applications using OWASP’s agentic risk categories. It covers ten risk areas and produces context-based severity ratings, findings, and remediation recommendations.

Key features

  1. 01Map architecture, autonomy, and oversight
  2. 02Assess OWASP’s ten agentic risk categories
  3. 03Rate severity by exploitability and context
  4. 04Document risk matrix and remediation

Use cases

  1. 01Review security risks in multi-agent applications
  2. 02Check tool permissions and component supply chains
  3. 03Organize findings and remediation priorities

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/owasp/secure-agent-playbook --skill agentic-ai-risk-assess

After installing, type/agentic-ai-risk-assessin Claude Code to confirm it loaded.

Details

From the project README

Agentic AI Risk Assessment

Evaluate agentic AI applications against all 10 risk categories by following the full procedure in plays/agentic-ai-risk-assess.md.

Steps

  1. Architecture Mapping — Identify agent type (single/multi-agent), autonomy level, tool ecosystem, memory systems, inter-agent communication protocols, and human oversight mechanisms.

  2. Assess Each Agentic Top 10 Risk:

    • ASI01 Agent Goal Hijack — Hidden prompts, instruction override, silent exfiltration via copilot patterns
    • ASI02 Tool Misuse — Legitimate tools bent into destructive outputs, tool parameter manipulation
    • ASI03 Identity & Privilege Abuse — Leaked credentials, excessive permissions, agent operating beyond scope
    • ASI04 Agentic Supply Chain — Poisoned MCP/A2A components, runtime component tampering, dynamic ecosystem risks
    • ASI05 Unexpected Code Execution — Natural language execution paths leading to RCE, code generation vulnerabilities
    • ASI06 Memory & Context Poisoning — Long-term behavior manipulation via memory attacks, context window exploits
    • ASI07 Insecure Inter-Agent Communication — Spoofed messages, man-in-the-middle between agents, cluster misdirection
    • ASI08 Cascading Failures — False signals propagating through automated pipelines, escalating impact chains
    • ASI09 Human-Agent Trust Exploitation — Confident misleading explanations, social engineering of human operators
    • ASI10 Rogue Agents — Misalignment, concealment, self-directed action, emergent harmful behavior

  3. Synthesize Findings — Assign severity based on exploitability and deployment context. Provide code locations, configuration gaps, and concrete remediation.

Output

Architecture overview, risk matrix (all 10 categories with status), detailed findings using templates/finding.md, positive controls observed, and prioritized recommendations.

OWASP References

  • OWASP Top 10 for Agentic Applications 2026
  • OWASP GenAI Security Project
  • OWASP Agentic Security Initiative

Comments

Markdown supported