Back to Skills Library
SafetyGuardrailsSecurityAI Agent Skill

ai-prompt-engineering-safety-review

Automated prompt safety review checking for jailbreaks, prompt injections, and sensitive data leakage.

github/awesome-copilot
10.1k stars
10.1k installs
Updated: 2026-06-14

Install Options

Install into Claude Code, Cursor, Codex, or Antigravity with:

$ npx skills add github/awesome-copilot@ai-prompt-engineering-safety-review

Real Work Situation Solved

Audit and guardrail against critical hallucinations before public release

The AI occasionally hallucinates fake promo policies or incorrect numbers - how do you install safety guardrails?

5-Step Action Framework

  1. 1List mission-critical facts that must never be wrong (pricing, legal terms, refund policies, PII).
  2. 2Deploy input guardrails: detect and reject jailbreak attempts and adversarial prompt injection.
  3. 3Deploy output verification: use regex and rule validation to cross-check numbers, links, and promo codes against the database.
  4. 4Define a deterministic fallback: when model confidence drops or checks fail, redirect to safe canned responses or human support.
  5. 5Log 100% of guardrail interventions into a review dashboard to feed ongoing eval benchmark updates.
Before

"Add a system prompt note: 'always answer accurately, never make things up'."

After

"Added a deterministic post-check: all generated prices must match the database exactly; on any mismatch, intercept and output official pricing link."

Related Course Lesson

AI Agents for PMLesson 9

Go to Lesson

SKILL.md Source Instructions

SKILL.md • Read-only preview
# AI Prompt Safety Review Skill

Audit prompts against OWASP Top 10 for LLMs, verify input sanitization, and enforce strict boundary tokens.