Run any Skill in Manus with one click

agent-security-audit

Stars123

Forks13

UpdatedMay 17, 2026 at 20:08

Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

OWASP

OWASP/secure-agent-playbook

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Information Security AnalystsComputer and Mathematical Occupations·SOC 15-1212

SKILL.md

readonly

name	agent-security-audit
description	Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup.
license	CC-BY-4.0

Agent Security Audit

Evaluate an AI agent's security posture by following the full procedure in plays/agent-security-audit.md.

Steps

Permission Inventory — Enumerate every tool, MCP server, file system path, network access, and credential the agent has. Flag capabilities beyond what its stated purpose requires.
Prompt Injection Surface Analysis — For each input path (user messages, tool outputs, MCP resources, RAG documents), assess whether crafted input could cause the agent to invoke unintended tools, override instructions, or exfiltrate data.
Excessive Agency Assessment (OWASP LLM06) — Check whether destructive/irreversible actions require confirmation, whether access exceeds need, whether the agent can escalate its own privileges, and whether individually-safe tool calls can chain into harmful outcomes.
Data Exfiltration Path Analysis — Map how sensitive data could leave the agent boundary: secrets passed to external tools, file contents in web requests, cross-MCP-server data forwarding, sensitive data in logs.
Tool-Call Injection Assessment — For each tool: can user-controlled input reach tool parameters unsanitized? Check for command injection, path traversal, SSRF, and SQL injection through agent-constructed calls.
Guardrail Evaluation — Check for system prompt safety instructions, tool call confirmations, output filtering, rate limiting, audit logging, and sandboxing.

Output

Use the finding format from templates/finding.md. Produce a Permission Summary table, Risk Findings, Injection Surface Map, and prioritized Recommendations.

OWASP References

LLM01: Prompt Injection
LLM02: Insecure Output Handling
LLM06: Excessive Agency
LLM07: System Prompt Leakage
LLM08: Vector and Embedding Weaknesses

More from this repository

same repository

mobile-code-review

OWASP/secure-agent-playbook

Security-focused review of native Android and iOS mobile app source code against OWASP MASVS v2.1.0. Use when reviewing mobile codebases, mobile PR diffs, or auditing a mobile module.

2026-06-02123

agentic-ai-risk-assess

OWASP/secure-agent-playbook

Assess agentic AI applications against the OWASP Top 10 for Agentic Applications 2026. Use when reviewing autonomous AI agents, multi-agent systems, or agentic workflows for security risks including goal hijacking, tool misuse, privilege abuse, and rogue agent behavior.

2026-05-17123

llm-risk-assess

OWASP/secure-agent-playbook

Comprehensive LLM security assessment against OWASP Top 10 for LLM Applications 2025. Use when reviewing LLM-integrated applications, RAG pipelines, chatbots, AI agents, or GenAI features. Covers prompt injection, data poisoning, supply chain, excessive agency, and more with real-world attack scenarios and testing methodologies.

2026-05-17123

mcp-server-review

OWASP/secure-agent-playbook

Security review of MCP (Model Context Protocol) server implementations and configurations. Use when auditing MCP server source code, evaluating third-party MCP servers before installation, or reviewing Claude Code MCP integrations for overpermissioning, injection risks, and data exposure.

2026-05-17123

prompt-injection-test

OWASP/secure-agent-playbook

Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments.

2026-05-17123

api-security-review

OWASP/secure-agent-playbook

Comprehensive API security review against OWASP API Security Top 10 (2023). Use when reviewing OpenAPI/Swagger specs, auditing REST/GraphQL/gRPC implementations, testing authentication mechanisms, or checking API gateway configurations. Covers BOLA/IDOR, broken auth, mass assignment, rate limiting, SSRF, and more with real-world attack scenarios.

2026-05-17123

name	agent-security-audit
description	Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup.
license	CC-BY-4.0

Agent Security Audit

Evaluate an AI agent's security posture by following the full procedure in plays/agent-security-audit.md.

Steps

Permission Inventory — Enumerate every tool, MCP server, file system path, network access, and credential the agent has. Flag capabilities beyond what its stated purpose requires.
Prompt Injection Surface Analysis — For each input path (user messages, tool outputs, MCP resources, RAG documents), assess whether crafted input could cause the agent to invoke unintended tools, override instructions, or exfiltrate data.
Excessive Agency Assessment (OWASP LLM06) — Check whether destructive/irreversible actions require confirmation, whether access exceeds need, whether the agent can escalate its own privileges, and whether individually-safe tool calls can chain into harmful outcomes.
Data Exfiltration Path Analysis — Map how sensitive data could leave the agent boundary: secrets passed to external tools, file contents in web requests, cross-MCP-server data forwarding, sensitive data in logs.
Tool-Call Injection Assessment — For each tool: can user-controlled input reach tool parameters unsanitized? Check for command injection, path traversal, SSRF, and SQL injection through agent-constructed calls.
Guardrail Evaluation — Check for system prompt safety instructions, tool call confirmations, output filtering, rate limiting, audit logging, and sandboxing.

Output

Use the finding format from templates/finding.md. Produce a Permission Summary table, Risk Findings, Injection Surface Map, and prioritized Recommendations.

OWASP References

LLM01: Prompt Injection
LLM02: Insecure Output Handling
LLM06: Excessive Agency
LLM07: System Prompt Leakage
LLM08: Vector and Embedding Weaknesses