Skip to main content
SAICA-KG

Tools

promptmap

1,181

Security scanner for custom LLM applications.

DetectionPost-generationFull HITLExperimentalTier 3Environment
Maturity tier details

Computed tier: 3(raw score 3.73). Effective tier: 3.

Facets:documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_commit=2stars=1.23

Source of truth:pipeline/maturity/score.py

Description

Promptmap is a CLI security scanner for custom LLM apps. Discovers system prompt leakage, prompt injection, and jailbreaks across user-provided endpoints. Designed for app-sec teams who want a quick adversarial sweep of their production LLM feature.

Why it's included

Fills the 'nmap-for-LLM-apps' niche: fast, single-purpose external scanner — complements broader scanners like garak which target the model rather than the deployed app.

Addresses failure modes

  • Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
  • Fabrication — Generating reference to non-existent APIs, packages, or symbols.
  • Scope creep — Actions outside declared task boundary.

Techniques

system-prompt-leak-probeprompt-injection-probejailbreak-probe

View raw YAML on GitHub →