Typosquatting in AI package suggestions
You asked an AI assistant for a Python helper to sanitize HTML, and it told you to `pip install htmlsanitizer-pro` and import it. The code looks clean and the package name sounds right. Before you add this dependency and run the install, what should you verify, and why is this specifically a risk with AI-suggested packages?
Implement
screen_dependency_suggestions(records: list[str], registry_names: list[str]) → list[str]Examples
in
[["bleach|52000000|1","htmlsanitizer-pro|0|0"],["bleach","nh3","html5lib"]]out["approved","hallucinated"]in
[["nh3|1200|1","sanitize-html-pro|140|1"],["nh3","sanitize-html-pro"]]out["approved","unvetted"]in
[["HTML5Lib|9000|1"],["html5lib"]]out["approved"]What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 10 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.