mcpField
P
prompt-governance

prompt-governance

github.com/borgheiSecurity1.0k65 installsUpdated 5d ago
Repository

About prompt-governance

A skill for auditing prompts for injection, bias, and safety concerns and maintaining a versioned catalog of approved prompts. It supports teams that review and govern prompts through a defined audit-to-deployment lifecycle.

Key features

  1. 01Injection, bias, and safety audits
  2. 02Versioned prompt catalog management
  3. 03Prompt version comparison
  4. 04Audit trail and rollback support

Use cases

  1. 01Review a prompt before approval
  2. 02Catalog and version approved prompts
  3. 03Compare prompt versions before promotion
  4. 04Roll back a prompt after an issue

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/borghei/claude-skills --skill prompt-governance

After installing, type/prompt-governancein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
prompt-governance-framework.md
scripts/
prompt_auditor.py
prompt_catalog_manager.py

Details

From the project README

Prompt Governance

Category: Engineering Domain: AI Governance

Overview

The Prompt Governance skill provides tools for auditing prompts for security vulnerabilities, bias, and safety issues, plus managing a versioned catalog of approved prompts. Essential for organizations deploying LLM-based applications at scale.

Clarify First

Before auditing or cataloging, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Target prompt(s) — the exact file/text to audit or the catalog dir to manage (the subject of every check)
  • Task: audit vs catalog management — selects prompt_auditor.py vs prompt_catalog_manager.py and the whole workflow
  • Check focus — injection / bias / safety (sets which auditor checks run and the pass/fail bar)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Quick Start

# Audit a prompt for security and safety issues
python scripts/prompt_auditor.py --file system_prompt.txt

# Audit with specific focus
python scripts/prompt_auditor.py --text "You are a helpful assistant..." --checks injection,bias,safety

# Initialize a prompt catalog
python scripts/prompt_catalog_manager.py --init --catalog-dir ./prompts

# Add a prompt to the catalog
python scripts/prompt_catalog_manager.py --add --name "customer-support-v1" --file prompt.txt --catalog-dir ./prompts

# List all prompts in catalog
python scripts/prompt_catalog_manager.py --list --catalog-dir ./prompts

Tools Overview

ToolPurposeKey Flags
prompt_auditor.pyAudit prompts for injection, bias, and safety--file, --text, --checks, --format
prompt_catalog_manager.pyManage versioned prompt catalog--init, --add, --list, --diff, --catalog-dir

Workflows

Prompt Review Process
  1. Author writes or modifies a prompt
  2. Run prompt_auditor.py for automated checks
  3. Review findings and address critical issues
  4. Add approved prompt to catalog with prompt_catalog_manager.py
  5. Deploy from catalog (never from ad-hoc sources)
Prompt Versioning
  1. Store all prompts in catalog with semantic versioning
  2. Use --diff to compare versions before promotion
  3. Maintain audit trail of all prompt changes
  4. Roll back to previous versions when issues detected

Reference Documentation

Common Patterns

Prompt Lifecycle

Draft -> Audit -> Review -> Approve -> Deploy -> Monitor -> Retire

Governance Checklist
  • No injection vulnerabilities
  • No harmful content generation potential
  • Appropriate bias mitigation
  • Clear scope boundaries
  • Output format constraints
  • Error handling instructions

Comments

Markdown supported