~ / directory / prompt-fuzzer
PF
Mixed · AI Red Teaming · reviewed 2026-04

Prompt Fuzzer

Open-source interactive prompt resilience testing tool.

01

What it does

An open-source interactive prompt resilience testing tool from Prompt Security. Generates and tests adversarial inputs against LLM system prompts to evaluate their robustness against injection and manipulation attacks.

02

Security relevance

Focused specifically on system prompt resilience — testing whether an LLM's instructions can be overridden, extracted, or bypassed. This is the core of LLM01 (Prompt Injection) and one of the most common real-world attack vectors.

03

When to use it

Use when hardening system prompts before deployment. Run against your production prompts to find injection vectors, then iterate on prompt design. Quick to set up via CLI, but requires understanding of prompt injection techniques to interpret results effectively.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 3 in LLM, 1 in Agentic.

Agentic Top 10 · 2026 · 1/10 covered
01
02
03
04
05
06
07
08
09
10
05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: Prompt Fuzzer
slug: prompt-fuzzer
type: Mixed
category: AI Red Teaming
url: https://github.com/prompt-security/ps-fuzz

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  [LLM01, LLM02, LLM06]
  asi:  [ASI01]

complexity:    Guided Setup
pricing:       —
audience:      Red Team
lifecycle:     [test]

tags: [CLI, Fuzzing, Open Source]