spec: usk/3.0 id: data-analyst-secure-suite version: 1.3.0 name: Secure Data Analyst Skill Suite description: A secure data analysis workflow suite based on MGC Blackbox 1.5.2+, providing credential protection, zero-exposure script & workflow application, sealed-package collaboration, and knowledge management. Supports MGC 1.5.2 workflow auto-recognition (import / from-import / relative paths / subprocess runtime routing). Includes a Data Analyst Agent system prompt template. author: MirginCipher Team license: MIT tags: security, data analysis, mgc, zero-exposure, local sandbox, credential management, workflow management, sealed collaboration, knowledge management, agent template, fuzzy search, auto-recognized workflow, sealed cross-script platform_compatibility: windows, macos, linux requires: mgc_blackbox: ">=1.5.2" changelog:

• version: 1.3.0 changes:
  • Upgraded to MGC 1.5.2+: added mgc_save_file (workflow folder storage), mgc_seal_package (workflow sealing), mgc_package (plaintext packaging).
  • Script management refactor: upgraded from single-script to workflow-folder mode, with import / from-import / relative-path / subprocess auto-recognition.
  • Credential management: unified info_type from 'credential' to 'token' to align with skill_spec.
  • Added prompts/collaboration_management.md: dedicated workflow / skill-package sealed-authorization guide.
  • Agent template: workflow examples upgraded from 5-step manual chain to find -> save_file -> run pattern.
  • Added sealed-collaboration chapter (mgc_seal_package one-click seal of an entire workflow).
  • Added recognizable cross-script patterns table (from-import / import / Path / subprocess).
  • MCP tools list expanded to 10 (added mgc_save_file, mgc_seal_package, mgc_package).
• version: 1.2.0 changes:
  • Synced with MGC Blackbox 1.4.10: added mgc_find (fuzzy search) and mgc_run (preferred over mgc_get action=run).
  • Script management: replaced mgc_get(action='run') with dedicated mgc_run tool.
  • Script management: added mgc_find workflow for locating scripts by name.
  • Script sealing: clarified ext04 must be a multi-line PEM public key.
  • Credential management: added mgc_find workflow.
  • Knowledge management: added mgc_find workflow.
  • Agent system prompt: documented the find -> get/run workflow pattern.
• version: 1.1.1 changes:
  • Optimized documentation structure per review report
  • Added 'Anti-patterns and pitfalls' chapter
  • Added 'Complete use cases' chapter
  • Unified prompt file-name references
• version: 1.1.0 changes:
  • Consolidated prompts into three core modules: credential, script, knowledge management
  • Added agent_system_prompt.md as a Data Analyst Agent system-prompt template
  • Strengthened document structure and clarified each module's scenario and invocation
• version: 1.0.0 changes:
  • Initial release

---

Overview

Secure Data Analyst Skill Suite is a documentation skill suite built on MGC Blackbox 1.5.2+ that helps data analysts securely manage, on the local machine:

• Sensitive credentials
• User-owned scripts and workflows
• Workflow / skill-package sealed authorization collaboration
• Analysis frameworks and knowledge

This suite uses a hybrid design:

• Skill prompts (under prompts/): four core capabilities — credential management, workflow management, sealed-collaboration, knowledge management
• Agent system-prompt template (agent_system_prompt.md): builds a Data Analyst Agent that obeys strict security boundaries

All sensitive operations require explicit user authorization. This suite provides no automated data-access capability.

---

Scenarios

This suite is suitable for:

• In-house enterprise data analysis
• Scenarios requiring sensitive-data protection
• Secure sharing of scripts / workflows in team collaboration
• Safe use of vendor scripts
• Building a secure Data Analyst Agent
• Building a knowledge accumulation system (can pair with a Self-Improving Agent)

---

Prerequisites

1. Install MGC Blackbox (≥ 1.5.2):

   pip install mgc-blackbox
   

2. Start the MGC service:

   mgc
   

3. Available MCP tools: mgc_save, mgc_save_file, mgc_get, mgc_run, mgc_seal, mgc_seal_package, mgc_package, mgc_list, mgc_find, mgc_open_webui
4. Token file: ~/.mgc/database/mgc_black_box/.mgc_token

---

Core capabilities

1. Credential management (credential_management.md)

Securely manage sensitive credentials such as database keys and API tokens.

Scenarios

• Need to connect to databases or external services
• Scripts need safe access to credentials
• Team members share database/service access rights (not the data itself)
• Team members share analysis methods and scripts across the team and outside (via workflow sealed authorization)

What it provides

• Local encrypted storage
• AI never sees credential content
• Scripts can call credentials with zero exposure
• All accesses require user authorization

How the agent uses it

After user authorization, the agent reads credentials but never sees plaintext.

---

2. Workflow management (script_management.md)

Manage user-owned query / clean / analyze scripts — both single-script and workflow-folder modes.

Scenarios

• User wants to apply their own scripts or workflows
• Scripts need safe access to credentials
• Multi-script workflows need auto-recognition of import / subprocess call relationships (1.5.2+)
• Workflows need cross-team collaboration (sealed)
• Need to build a complete data-analysis chain (query → clean → analyze)

What it provides

• Single-script encrypted storage (mgc_save)
• Workflow-folder encrypted storage with auto-recognition of import / subprocess (mgc_save_file, 1.5.2+)
• AI never sees script content
• Scripts call credentials with zero exposure
• Supports single-script sealing (mgc_seal) and workflow sealing (mgc_seal_package)
• All applications require user authorization

How the agent uses it

After user authorization, the agent runs scripts or workflows through MGC. In workflow mode, MGC auto-recognizes the import chain — no manual parameter chaining needed.

---

3. Sealed-authorization collaboration (collaboration_management.md)

Seal-authorize workflows and skill packages to other nodes, enabling "usable but not readable, runnable but not resellable" cross-team / cross-organization collaboration.

Scenarios

• Data team seals an analysis workflow to a business team (run only, no source access)
• Vendor analyst seals an analysis solution to a client
• Cross-department sharing of analysis methodologies while protecting core logic
• Independent license per client

What it provides

• Workflow sealing (mgc_seal_package): seal the entire workflow in one call, AES-256 encryption
• Skill-package sealing: seal a complete skill package (with SKILL.md); receiving AI can read the instructions but cannot see source code
• Node binding: AES key bound to the target node's RSA public key; cannot be re-sealed
• One-key-per-node: each client receives an independent key
• No cloud: all encryption / decryption / execution happens locally

How the agent uses it

After user authorization, the agent performs the sealing operation. The sealed package is delivered by the user manually — the agent does not participate in transport.

---

4. Knowledge management (knowledge_management.md)

Manage knowledge assets: analysis frameworks, prompt templates, methodologies, business rules, and more.

Scenarios

• Build standardized analysis frameworks
• Reuse prompt templates
• Share analysis methods across the team
• Build a knowledge accumulation system
• Pair with a Self-Improving Agent for automatic knowledge capture

What it provides

• Encrypted storage of knowledge content
• Agent reads knowledge with explicit user authorization
• Knowledge sealed collaboration supported
• Used to build analysis-report structure

How the agent uses it

After user authorization, the agent reads knowledge and uses it to guide analysis structure or generate prompts.

---

Security boundary

This suite provides

• Local encrypted credential storage
• Zero-exposure application of user-owned scripts
• Workflow auto-recognition and sealed routing (1.5.2+, including subprocess literal-list runtime routing)
• Sealed-authorization collaboration for workflows / skill packages (1.5.2+)
• Knowledge encryption management

This suite does NOT provide

• Automated data access
• Automated cleaning or analysis
• Automated transport
• Script generation or modification

All scripts must be user-provided and comply with organizational policy.

---

File structure

data-analyst-secure-suite/
├── SKILL.md                    # main document (this file)
├── README.md                   # detailed usage guide
├── manifest.json               # skill metadata
├── agent_system_prompt.md      # Agent system-prompt template
└── prompts/
    ├── credential_management.md    # credential management
    ├── script_management.md        # workflow & script management
    ├── collaboration_management.md # sealed collaboration
    └── knowledge_management.md     # knowledge management

---

Usage modes

Mode 1 — Skill mode

The AI can read the four core prompts under prompts/:

Document	When to use	Triggered by
credential_management.md	Need to store or access credentials	user or agent
script_management.md	Need to store or run a script/workflow	user or agent
collaboration_management.md	Need to seal a workflow / skill package to another node	user or agent
knowledge_management.md	Need to store or read knowledge	user or agent

The AI cites the matching document on user request and asks for authorization before every sensitive operation.

---

Mode 2 — Agent template mode

Set agent_system_prompt.md as the system prompt for an AI Agent.

The agent will automatically enforce:

• Request user authorization before every sensitive operation
• Only apply scripts or workflows through MGC Blackbox
• Never view script content or credentials
• Never automate workflow execution
• Never auto-select a script name (info_owner must be supplied by the user)

After authorization, the agent may cite documents under prompts/ as workflow guidance.

---

MCP tools reference

Tool	Description	Authorization required
mgc_save	Store credentials, single scripts, prompts	yes
mgc_save_file	Store workflow folders (auto-recognize import / subprocess)	yes
mgc_get	Retrieve a value / fetch node_pub	yes
mgc_run	Run a script or workflow (black-box)	yes
mgc_seal	Seal a single script for collaboration	yes
mgc_seal_package	Seal an entire workflow folder	yes
mgc_package	Plaintext packaging within the same trust zone	yes
mgc_list	List stored entries (exact match)	optional
mgc_find	Fuzzy-search entries by name	optional
mgc_open_webui	Open MGC WebUI	no

---

Security notes

1. Zero exposure: scripts and credentials execute locally; the AI receives only run status
2. Encrypted storage: all content encrypted at rest
3. No plaintext leak: the AI never sees script or credential content
4. Auto-recognized workflows: import / from-import / relative-path / subprocess call chains auto-routed; nothing lands on disk (1.5.2+)
5. Sealed workflows / skill packages: entire workflow or skill package sealed to the target node in one call; node-bound; cannot be resold (1.5.2+)

---

Contact

• Issues: https://github.com/zkeviny/MGC-Blackbox/issues
• Email: mirgincipher@outlook.com

---

Reminder: This suite is for secure workflow management. All sensitive operations must have explicit user authorization. All scripts are user-owned; all execution happens locally through MGC Blackbox.