Lesson 43 of 65 · Free to read
Day 43 — AI security: secret leakage, prompt/code injection, insecure or “sl…
Month 3 · Week 9 — Quality, Testing, Security & Responsible AI Audience: Final-year students & early-career engineers (0–3 years) Format: Self-paced study + optional live clinic · Suggested time: 4–6 focused hours Key tools: Cursor, Snyk / Dependabot
Overview
AI security risks: secret leakage, prompt/code injection, slopsquatted dependencies, license contamination. Treat model suggestions as untrusted input.
Learning objectives
By the end of this session, you can:
- Explain the core ideas behind: AI security: secret leakage, prompt/code injection, insecure or “slopsquatted” dependencies, license risk.
- Apply the ideas using Cursor, Snyk / Dependabot on a realistic task (capstone, internship, or first-job style)
- Produce the exercise deliverable with clear success criteria
- Identify common failure modes and how to recover
- Capture at least one reusable prompt, rule, or checklist for your personal library
- Decide what must remain human-reviewed for this class of work
Core concepts
Threat sketches
- Secrets in prompts/repos
- Dependency typosquatting from invented package names
- XSS/SQLi from generated handlers
- License copy-paste from unknown snippets
Tooling
Secret scanning, Dependabot/Snyk, lockfile discipline, allowlists.
Tooling for today
Primary tools: Cursor, Snyk / Dependabot. Prefer official docs when APIs change. When a model invents a symbol, verify against source or docs immediately.
Practice posture
You are a final-year or early-career engineer pairing with a very fast teammate (the model): clear intent, grounded context, inspect consequential changes, keep a paper trail (commits, prompts, decisions).
Process diagram
Watch & learn
Study these free videos before or during the exercise. Each embed is chosen to reinforce today's objectives.
Course video
Worked example / case study
Scenario
Security pass on your app; fix issues; add secret scanning.
Step-by-step
- Clarify the outcome in one sentence tied to the exercise below.
- Gather grounding context (files, docs, schema, acceptance checks).
- Run the primary tool(s): Cursor, Snyk / Dependabot.
- Produce the smallest vertical slice that proves the idea.
- Verify with a command, test, screenshot, or side-by-side comparison.
- Write down one steering note — what you told the AI when it went wrong.
Sample prompt you can adapt
Role: Senior engineer mentoring an early-career developer (pairing with me).
Task: AI security: secret leakage, prompt/code injection, insecure or “slopsquatted” dependencies, license risk.
Context: Final-year / early-career project (capstone, internship, or junior role).
Constraints:
- Match existing project patterns
- No new dependencies unless justified
- Include tests or a verification checklist
- Call out assumptions explicitly
Output: step plan first, then code/files, then verification commands.
Hands-on exercise
Primary task. Run a security pass, fix the vulnerabilities, and add secret scanning to the repo.
Coaching notes
Add a SECURITY.md with reporting contact.
Steps
- Set up or open the workspace required by: Cursor, Snyk / Dependabot.
- Skim today's core concepts and watch the video(s) before prompting.
- Execute the task in small commits (or saved artifacts if no-code).
- Fill the success checklist below.
- Note one surprise and one process improvement for tomorrow.
Success criteria
- Deliverable matches the exercise description
- You can explain every AI-generated change in plain language
- Verification ran (tests, manual check, or published URL)
- At least one pitfall from this lesson was consciously avoided
- Artifact saved (repo commit, doc, or published link)
Timebox
Suggested: 90–150 minutes of focused build time after study.
Templates & checklists
| Asset | Purpose |
|---|---|
| Prompt stub | Reuse today's structure (role → task → constraints → format) |
| Verification checklist | Tests / manual QA / security skim |
| Decision log | What you delegated vs kept human |
Copy-paste prompt skeleton
## Goal
AI security: secret leakage, prompt/code injection, insecure or “slopsquatted” dependencies, license risk.
## Context files
- (list paths)
## Constraints
- Stack: (fill)
- Do not: (secrets, drive-by refactors)
## Definition of done
- Run a security pass, fix the vulnerabilities, and add secret scanning to the repo.
Daily reflection (3 minutes)
- What did AI do well?
- Where did it confidently fail?
- What rule will you add to your cookbook/rules file?
Common pitfalls
- Installing packages you did not look up
- Disabling hooks to 'move fast'
- Ignoring license texts in generated code
Key takeaways
- Untrusted input includes AI output
- Scanners are mandatory teammates
- Package name hallucination is a real incident class
- Tools (Cursor, Snyk / Dependabot) change; the judgment skills transfer.
Resources
- Official docs for: Cursor, Snyk / Dependabot
- Course cookbook: keep prompts in a versioned Markdown file in your repo
- Prior days this week — skim objectives if you skipped ahead
Self-paced lesson — Mastering AI-Assisted Development & Vibe Coding — Day 43 of 65.