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.

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

Tool	Purpose	Key Flags
`prompt_auditor.py`	Audit prompts for injection, bias, and safety	`--file`, `--text`, `--checks`, `--format`
`prompt_catalog_manager.py`	Manage versioned prompt catalog	`--init`, `--add`, `--list`, `--diff`, `--catalog-dir`

Workflows

Prompt Review Process

Author writes or modifies a prompt
Run prompt_auditor.py for automated checks
Review findings and address critical issues
Add approved prompt to catalog with prompt_catalog_manager.py
Deploy from catalog (never from ad-hoc sources)

Prompt Versioning

Store all prompts in catalog with semantic versioning
Use --diff to compare versions before promotion
Maintain audit trail of all prompt changes
Roll back to previous versions when issues detected

Reference Documentation

Prompt Governance Framework - Policies, review processes, and compliance requirements

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

prompt-governance