Slopsquatting
Slopsquatting is an attack in which adversaries register malicious software packages whose names resemble dependencies hallucinated or suggested by language models.
Introduction to Generative AI, Second Edition
Slopsquatting is an attack in which adversaries register malicious software packages whose names resemble dependencies hallucinated or suggested by language models.
- How it is used
- Frames slopsquatting as a risk of accepting AI-suggested dependencies without checking their origin.
- How deep it goes
- Explains the attack pathway and mitigation efforts, distinguishing invented package names from names resembling legitimate packages.
- Examples
- Uses malicious packages registered under model-suggested names to illustrate how an installation can compromise a project.
- What you can do after
- Evaluate suggested dependencies by recognizing the risk of installing packages without verifying their origin.
Read how Introduction to Generative AI, Second Edition explains slopsquatting →
Vibe Engineering
An attack in which an attacker registers package names that language models are likely to hallucinate so developers may install malicious software.
- How it is used
- Frames AI-suggested dependencies as a supply-chain security decision requiring verification before installation.
- How deep it goes
- Explains the attack mechanism, gives observed rates and a concrete incident, then stops short of analyzing malicious payload implementation.
- Examples
- Uses the hallucinated huggingface-cli package, PyPI registration, and documented hallucination-rate studies as evidence.
- What you can do after
- Operate dependency controls by verifying package existence, reviewing necessity, and running vulnerability, license, and supply-chain scans.
What to know first
- conversational aiConversational AI is artificial intelligence that enables software systems to interpret user input and interact with users through natural-language dialogue.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
Related concepts
- package hallucinationcontrasts with · A package hallucination is an AI-generated reference to a nonexistent, unsupported, or incorrectly identified software package.
- malwareproduces · Malware is software or executable code intentionally designed to perform harmful, unauthorized, deceptive, or security-compromising actions on systems or data.
- hallucinationuses · A hallucination is model-generated content that is false, fabricated, or unsupported by relevant evidence but presented as plausible or factual.
Questions about slopsquatting
What is slopsquatting?
Slopsquatting is an attack in which adversaries register malicious software packages whose names resemble dependencies hallucinated or suggested by language models.
Which Manning books explain slopsquatting?
Introduction to Generative AI, Second Edition and Vibe Engineering.
What should I know before learning slopsquatting?
Manning books that teach slopsquatting usually introduce conversational ai and language model first.
What is the difference between slopsquatting and package hallucination?
Slopsquatting is an attack in which adversaries register malicious software packages whose names resemble dependencies hallucinated or suggested by language models. A package hallucination is an AI-generated reference to a nonexistent, unsupported, or incorrectly identified software package.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

