ps-fuzz
Test and harden system prompts for GenAI apps to ensure safety and security.
GraphCanon updated 2w · GitHub synced 2w
Decision brief
Good fit when
- When you need to methodically test system prompts in generative AI applications for potential security flaws.
- To ensure safety and security of GenAI apps by identifying vulnerabilities through prompt fuzzing.
Avoid when
- If your project does not involve generative AI applications or does not require prompt testing for security reasons.
- For tasks unrelated to the hardening and evaluation of system prompts, as ps-fuzz is specifically designed for this purpose.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (169d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install ps-fuzz PyPISimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A tool that tests generative AI applications through systematic prompt fuzzing to identify vulnerabilities and improve overall security of the systems.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 5, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 5, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
🚀 Installation
-
Install the Fuzzer package
Using pip install
pip install prompt-security-fuzzerUsing the package page on PyPi
You can also visit the package page on PyPi
Or grab latest release wheel file form releases
-
Launch the Fuzzer
export OPENAI_API_KEY=sk-123XXXXXXXXXXXX prompt-security-fuzzer -
Input your system prompt
-
Start testing
-
Test yourself with the Playground! Iterate as many times are you like until your system prompt is secure.
For agents
This page has a .md twin and JSON over the API.