utkusen/promptmap

a security scanner for custom LLM applications

51
/ 100
Established

Employs a dual-LLM architecture where a controller model evaluates whether attack payloads successfully compromise the target application, enabling both white-box testing (direct model access with system prompts) and black-box testing (HTTP endpoints). Includes 50+ pre-built YAML-configurable rules across prompt stealing, jailbreaking, and bias categories, with support for OpenAI, Anthropic, Google, XAI, and local Ollama models.

1,146 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,146

Forks

120

Language

Python

License

GPL-3.0

Last pushed

Dec 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/utkusen/promptmap"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.