Show HN: Phantom Guard – Detect AI-hallucinated package attacks(github.com)
github.com
Show HN: Phantom Guard – Detect AI-hallucinated package attacks
https://github.com/matte1782/phantom_guard
2 comments
does this end up flagging legit packages that just have 'ai' or 'gpt' in the name? feels like half of pypi would trigger at this point
Great question! No, Phantom Guard won't flag legit packages like openai, langchain-openai, or gpt-engineer.
The primary signal is whether the package exists on the registry. We query PyPI/npm directly:
- If a package exists → it gets a low/safe risk score
- If a package doesn't exist → that's the main red flag for slopsquatting
Pattern matching (like AI-related terms) is just one of many weighted signals, and it's far outweighed by existence. In fact, popular packages get a negative weight that actively reduces their risk score.
The attack we're detecting is when an LLM hallucinates a package name like flask-gpt-utils that sounds plausible but doesn't exist. A real attacker could then register that name and wait for developers to pip install it.
We test against the top 1000 PyPI packages and target <5% false positive rate. If you're importing openai or transformers, you're fine.
The attack vector: AI assistants hallucinate package names → attackers register those names with malware → developers install malware thinking it's legit.
How it works: 1. Checks if packages exist on registries 2. Matches against 10+ AI hallucination patterns 3. Detects typosquats of top 3000 packages 4. Analyzes metadata (age, downloads, maintainers)
``` pip install phantom-guard phantom-guard validate flask-gpt-helper # HIGH_RISK: Package not found, matches pattern ```
Performance: <10ms cached, <200ms uncached.
Try the live demo: https://matte1782.github.io/phantom_guard/
GitHub: https://github.com/matte1782/phantom_guard