ワンクリックでManusで任意のスキルを実行

ingest-mcp-proxy-ocsf

スター3

フォーク0

更新日2026年7月10日 03:53

Convert raw MCP proxy logs (from agent-bom proxy or any MCP JSON-RPC middleware) into Application Activity records. OCSF 1.8 (class 6002) is the default output, with a native projection available via `--output-format native`. Every event carries session_uid, JSON-RPC method, direction, and a stable tool fingerprint (sha256 of name + description + inputSchema + annotations) so downstream detection skills can spot schema drift. Use when the user mentions MCP proxy logs, OCSF ingestion, detection engineering pipeline, or wants to feed MCP traffic into a SIEM or detection stack. Do NOT use for CloudTrail, GCP audit, Azure Activity, or K8s audit logs (use ingest-cloudtrail-ocsf / ingest-gcp-audit-ocsf / ingest-azure-activity-ocsf / ingest-k8s-audit-ocsf respectively). Do NOT use as a detection skill — this skill only normalises, it does not flag anything.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

msaad00

msaad00/cloud-ai-security-skills

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

関連職種SOC

SOC 職業分類に基づく

情報セキュリティアナリストコンピュータ・数学職·SOC 15-1212

ファイルエクスプローラー

6 ファイル

SKILL.md

readonly

このリポジトリの他の Skills

同じリポジトリ

cspm-azure-cis-benchmark

msaad00/cloud-ai-security-skills

Assess Azure subscriptions against a curated subset of CIS Azure Foundations Benchmark v2.1. Automates 32 high-impact read-only checks across Identity, Defender for Cloud, Storage, Database, Logging, Networking, Compute, Key Vault, and App Service (~53% of the v2.1 benchmark). Use when the user mentions Azure CIS benchmark, Azure storage security, or unrestricted SSH/RDP detection in NSGs. Do NOT use for AWS or GCP; do NOT use to remediate findings (assessment-only, Reader role only); do NOT claim full CIS Azure coverage — only 32 of 60 controls are implemented, see the Roadmap section in this file for the gap.

2026-07-113

ingest-entra-directory-audit-ocsf

msaad00/cloud-ai-security-skills

Convert verified Microsoft Entra directoryAudit events into OCSF 1.8 API Activity (6003). The first slice maps Microsoft Graph directory audit events for service-principal credential changes, app-role grants, and federated identity credential creation into deterministic OCSF records while preserving Entra natural IDs such as id, correlationId, and activityDateTime for SIEM dedupe and downstream correlation. Use when the user mentions Entra audit log ingestion, Microsoft Graph directoryAudit normalization, or feeding Entra identity telemetry into an OCSF pipeline. Do NOT use for Okta System Log, Azure Activity Logs, or as a detector or policy engine — this skill only normalizes verified Microsoft Graph directoryAudit payloads.

2026-07-113

ingest-k8s-audit-ocsf

msaad00/cloud-ai-security-skills

Convert raw Kubernetes audit logs (`audit.k8s.io/v1`) into normalized API activity records, with OCSF as the default wire format and native output as an option. Maps user, source IP, verb, objectRef, and response status with enough fidelity for K8s privilege-escalation and secret-access detectors. Use when the user mentions Kubernetes audit logs, kube-apiserver audit sinks, K8s detection engineering, or feeding K8s audit into a SIEM. Do NOT use for container runtime logs, kubelet logs, or CloudTrail / GCP audit / Azure Activity. Do NOT use as a detection skill; this only normalizes events.

2026-07-113

ingest-okta-system-log-ocsf

msaad00/cloud-ai-security-skills

Convert verified Okta System Log events into OCSF 1.8 or native Identity & Access Management records. The first slice maps session and SSO events to Authentication (3002), user lifecycle and account-control changes to Account Change (3001), app/group membership updates to User Access Management (3005), and a narrow verified set of Okta Verify MFA challenge and denial events to Authentication (3002). It preserves Okta natural IDs such as uuid, published, transaction.id, and authenticationContext.externalSessionId for SIEM-friendly dedupe and correlation. Use when the user mentions Okta System Log ingestion, Okta audit log normalization, cross-vendor identity telemetry, or feeding Okta identity events into an OCSF pipeline or native canonical-first flow. Do NOT use for raw Azure Entra, Google Workspace, or AWS IAM logs. Do NOT use as a detector or policy engine — this skill only normalizes verified Okta event payloads into OCSF or native output.

2026-07-113

detect-aws-access-key-creation

msaad00/cloud-ai-security-skills

Detect successful AWS IAM `CreateAccessKey` API calls against IAM users from OCSF 1.8 API Activity records emitted by ingest-cloudtrail-ocsf. Emits an OCSF 1.8 Detection Finding (class 2004) tagged with MITRE ATT&CK T1098.001 (Additional Cloud Credentials) when a principal creates an access key for an IAM user. Use when the user mentions "AWS access key created", "IAM user key issuance", "additional cloud credentials in AWS", or "T1098.001 via CloudTrail". Do NOT use as a posture-at-rest access-key inventory check, to infer console-password or login-profile creation, or to claim every AWS identity-pivot path. This first slice only covers successful `CreateAccessKey` operations.

2026-07-103

detect-mcp-tool-drift

msaad00/cloud-ai-security-skills

Detect MCP tool schema drift mid-session — the MCP tool-poisoning / rug-pull attack pattern. Reads OCSF 1.8 Application Activity (class 6002) or the native application-activity projection produced by ingest-mcp-proxy-ocsf, groups them by session, and flags any tool whose fingerprint (sha256 over name + description + inputSchema + annotations) changes between tools/list responses in the same session. Emits OCSF 1.8 Detection Finding (class 2004) with MITRE ATT&CK T1195.001 (Compromise Software Supply Chain) inside finding_info.attacks. Use when the user mentions MCP security, tool drift, tool poisoning, prompt injection via tool schema, or supply chain compromise of an MCP server. Do NOT use on raw MCP proxy logs — feed them through ingest-mcp-proxy-ocsf first. Do NOT use for cross-session drift (same tool, different sessions) — that is a legitimate MCP server update, not an attack; a separate detector will cover it. Do NOT use for divergence against an out-of-band server-registered baseline — that is detect-m

2026-07-103

name	ingest-mcp-proxy-ocsf
description	Convert raw MCP proxy logs (from agent-bom proxy or any MCP JSON-RPC middleware) into Application Activity records. OCSF 1.8 (class 6002) is the default output, with a native projection available via `--output-format native`. Every event carries session_uid, JSON-RPC method, direction, and a stable tool fingerprint (sha256 of name + description + inputSchema + annotations) so downstream detection skills can spot schema drift. Use when the user mentions MCP proxy logs, OCSF ingestion, detection engineering pipeline, or wants to feed MCP traffic into a SIEM or detection stack. Do NOT use for CloudTrail, GCP audit, Azure Activity, or K8s audit logs (use ingest-cloudtrail-ocsf / ingest-gcp-audit-ocsf / ingest-azure-activity-ocsf / ingest-k8s-audit-ocsf respectively). Do NOT use as a detection skill — this skill only normalises, it does not flag anything.
purpose	Convert raw MCP proxy logs (from agent-bom proxy or any MCP JSON-RPC middleware) into Application Activity records.
capability	ingest
persistence	none
telemetry	stderr_jsonl
privilege_escalation	none
license	Apache-2.0
approval_model	none
execution_modes	jit, ci, mcp, persistent
side_effects	none
input_formats	raw
output_formats	native, ocsf
concurrency_safety	stateless

ingest-mcp-proxy-ocsf

Thin, single-purpose ingestion skill: raw MCP proxy JSONL in → OCSF 1.8 Application Activity JSONL by default, or the repo-owned native application-activity projection when requested. No detection logic, no side effects, no external calls.

Wire contract

Reads the format emitted by the agent-bom proxy command:

{
  "timestamp":  "2026-04-10T05:00:00.000Z",
  "session_id": "sess-abc",
  "method":     "tools/list",
  "direction":  "response",
  "body":       { "tools": [ ... ] }
}

Writes OCSF 1.8 Application Activity (class 6002) with the cloud_security_mcp custom profile. See ../OCSF_CONTRACT.md for the field-level pinning.

Usage

# Single file, OCSF default
python src/ingest.py mcp-proxy.jsonl > mcp-proxy.ocsf.jsonl

# Native projection
python src/ingest.py mcp-proxy.jsonl --output-format native > mcp-proxy.native.jsonl

# Piped from a running proxy
agent-bom proxy "<server cmd>" --log-format jsonl \
  | python src/ingest.py \
  | python ../detect-mcp-tool-drift/src/detect.py \
  > findings.ocsf.jsonl

Native output format

When --output-format native is selected, the skill emits the repo-owned canonical projection instead of the OCSF envelope. Each record includes:

schema_mode: "native"
canonical_schema_version
record_type: "application_activity"
event_uid
provider
time_ms
session_uid
method
direction
tool when the source event declares a tool

Example:

{
  "schema_mode": "native",
  "canonical_schema_version": "2026-04",
  "record_type": "application_activity",
  "event_uid": "7a1c...",
  "provider": "MCP",
  "time_ms": 1775797200000,
  "session_uid": "sess-abc",
  "method": "tools/list",
  "direction": "response",
  "tool": {
    "name": "query_db",
    "fingerprint": "sha256:..."
  }
}

Fingerprint

For every tools/list response entry and every tools/call request, the skill emits an OCSF event with a stable mcp.tool.fingerprint:

fingerprint = sha256(json.dumps({
    "name":        tool["name"],
    "description": tool.get("description", ""),
    "inputSchema": tool.get("inputSchema", {}),
    "annotations": tool.get("annotations", {}),
}, sort_keys=True).encode()).hexdigest()

This is the pivot point for detection skills. Anything that makes the fingerprint change = tool drift.

Behaviour on malformed input

One bad line → warning to stderr, skipped, pipeline continues.
Missing timestamp → current time.
Missing session_id → "sess-unknown" (detected by downstream detection skills).
Empty file → zero output lines, exit 0.

Tests

tests/test_ingest.py runs the skill against ../golden/mcp_proxy_raw_sample.jsonl and asserts the output matches ../golden/mcp_proxy_sample.ocsf.jsonl with volatile fields scrubbed.