Generated banner for Owasp MCP
Generated logo for Owasp MCP

Owasp MCP

MicrosoftOfficialPublished by Microsoft

  • Skill
  • Guidelines
  • Security
  • CC-BY-SA-4.0
  • Medium risk

From the author

OWASP MCP Top 10 knowledge base for identifying, assessing, and remediating Model Context Protocol security risks.
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The owasp-mcp skill provides a comprehensive, machine-readable reference for the OWASP MCP Top 10 (2025). It is designed to help developers and security professionals identify, assess, and remediate common security vulnerabilities inherent in Model Context Protocol architectures. By structuring these risks into standardized documents, the skill enables AI agents to perform security audits, provide defensive guidance, and suggest remediation strategies for issues ranging from credential mismanagement to tool poisoning and shadow server deployment.

What it does

  • Provides a structured index of the OWASP MCP Top 10 security vulnerabilities.
  • Offers detailed descriptions, impact assessments, and vulnerability checklists for each risk.
  • Supplies defensive design patterns and prevention controls for MCP architectures.
  • Includes realistic attack scenarios to help visualize potential exploitation paths.
  • Provides actionable detection signals and remediation steps for security incidents.

When to use it

  • During the design phase of an MCP server or client to implement secure-by-design principles.
  • When auditing an existing MCP implementation for potential security gaps.
  • To train or prompt an AI agent to assist in identifying security risks within an MCP-based workflow.
  • When responding to a suspected security incident involving MCP tool calls or context sharing.

Advantages

  • Aligned with industry-standard OWASP security research.
  • Structured for machine-readability, making it ideal for AI-assisted security analysis.
  • Covers a broad spectrum of risks specific to the Model Context Protocol ecosystem.
  • Provides clear, actionable remediation guidance for developers.

Usage examples

“What are the security risks associated with tool poisoning in an MCP environment?”
The agent will reference the MCP03:2025 documentation to explain the risks of tool poisoning, provide a checklist for identifying vulnerable configurations, and suggest prevention controls.
“How can I prevent secret exposure in my MCP server implementation?”
The agent will retrieve the MCP01:2025 reference to outline best practices such as using secure vaults, enforcing short-lived tokens, and implementing log redaction.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/owasp-mcp/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip owasp-mcp.zip -d .agents/skills

Documentation by Microsoft

OWASP® MCP Top 10 — Skill Entry

This SKILL.md is the entrypoint for the MCP Vulnerabilities skill.

The skill encodes the OWASP MCP Top 10 (2025) as structured, machine-readable references that an agent can query to identify, assess, and remediate MCP security risks.

Normative references (MCP Top 10)

  1. 00 Vulnerability Index

  2. 01 Token Mismanagement and Secret Exposure

  3. 02 Privilege Escalation via Scope Creep

  4. 03 Tool Poisoning

  5. 04 Software Supply Chain Attacks and Dependency Tampering

  6. 05 Command Injection and Execution

  7. 06 Prompt Injection via Contextual Payloads

  8. 07 Insufficient Authentication and Authorization

  9. 08 Lack of Audit and Telemetry

  10. 09 Shadow MCP Servers

  11. 10 Context Injection and Over-Sharing

Skill layout

  • SKILL.md — this file (skill entrypoint).

  • references/ — the MCP Top 10 normative documents.

    • 00-vulnerability-index.md — index of all vulnerability identifiers, severities, and cross-references.

    • 01 through 10 — one document per vulnerability aligned with OWASP MCP numbering.

Third-Party Attribution

Copyright © OWASP Foundation. OWASP® MCP Top 10 content is derived from works by the OWASP Foundation, licensed under CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). Source: https://owasp.org/www-project-mcp-top-10/ Modifications: Vulnerability descriptions restructured into agent-consumable reference documents with added detection and remediation guidance. OWASP® is a registered trademark of the OWASP Foundation. Use does not imply endorsement.

Files

references/08-lack-of-audit-telemetry.md


title: 'MCP08: Lack of Audit and Telemetry' description: OWASP MCP Top 10 reference for audit and telemetry vulnerabilities including logging gaps and observability deficiency patterns

08 Lack of Audit and Telemetry

Identifier: MCP08:2025 Category: Observability

Description

MCP systems orchestrate complex, autonomous workflows performing data retrieval, tool execution, and decision-making with minimal human intervention. When audit logging and telemetry are absent or poorly implemented, organizations lose visibility into agent actions, data access patterns, and decision provenance. This gap undermines incident response, obscures compliance violations and insider abuse, and allows unmonitored agents to silently perform sensitive operations or exfiltrate data for extended periods without detection.

Impact

  • No traceability for agent actions or context decisions.

  • Compliance failure with GDPR, PCI DSS, ISO 27001 requirements.

  • Delayed breach detection increasing dwell time and damage.

  • Integrity loss making outcome verification impossible.

  • Operational blind spots hiding model drift, behavioral anomalies, or prompt injections.

  • Regulatory penalties and reputation damage from inability to demonstrate due diligence.

Vulnerability checklist

  • Agent activity is not logged in a structured, centralized format.

  • Logs are stored locally, deleted frequently, or lack integrity protections.

  • Tool invocations, prompt contents, and system events are not captured or correlated.

  • No integration with SIEM/XDR or centralized monitoring platforms.

  • Logs do not include user identity, timestamps, or schema versioning.

  • No alerting for anomalous tool use or unauthorized API calls.

  • Privacy concerns led to overly broad log suppression instead of redaction.

  • Audit retention policies are undefined or misaligned with compliance requirements.

Prevention controls

  1. Log all agent actions, tool invocations, schema versions, and context snapshots in structured format (JSON, CEF, OTEL).

  2. Apply cryptographic hashing (HMAC, SHA-256) to log files for integrity.

  3. Store logs in append-only or write-once media (S3 Object Lock, WORM storage).

  4. Forward MCP logs to enterprise SIEM systems for correlation.

  5. Establish automated alert rules for high-risk activities.

  6. Implement PII-safe logging with tokenization or field-level encryption.

  7. Build behavioral baselines and use anomaly detection for deviations.

  8. Restrict log access with separation of duties and least privilege.

  9. Use OpenTelemetry or equivalent to trace requests across the MCP pipeline.

  10. Align log retention with applicable compliance frameworks.

Example attack scenarios

Scenario A — Silent exfiltration

A compromised healthcare analytics agent exports small amounts of patient data via legitimate tool calls and the breach remains undetected for months because telemetry is disabled.

Scenario B — Insider manipulation

A developer disables telemetry for a testing session and uses the agent to extract pricing model data with no audit trail to establish accountability.

Scenario C — Prompt injection leading to data theft

A malicious PDF causes an agent to retrieve credentials and send them to an external domain. No logs exist for context transformations or network calls.

Scenario D — Drift without detection

A compliance bot drifts in behavior after retraining cycles, approving violating actions. Without telemetry and baselines, changes go unnoticed until a manual audit months later.

Detection signals

  • Gaps or inconsistencies in audit trails.

  • Unexplained spikes in API billing, latency, or resource consumption.

  • Lack of log entries during active usage periods.

  • Incident response teams reporting "no data available" during investigations.

  • Sudden drops in telemetry ingestion volume.

Remediation

  • Re-enable detailed logging at all MCP layers (agent, tool, network).

  • Deploy forwarders to central SIEM/XDR with retention guarantees.

  • Implement masking and pseudonymization for privacy-sensitive fields.

  • Reconstruct minimal timeline from external system logs.

  • Enforce mandatory logging for all MCP agents going forward.

Requirements and compatibility

Written for: GitHub Copilot, Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter, Needs an MCP server

Security

What our scanner noticed· Medium risk

  • References to credential files

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/hve-core · .github/skills/security/owasp-mcp · commit f425e94
Licence
Creative Commons Attribution-ShareAlike 4.0 International (redistribution allowed)
  • LICENSE (written by AutoGineer)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download owasp-mcp.zip