GraphCanon updated Oct 22, 2026 · GitHub synced Oct 22, 2026
Decision brief
Unverified catalog guidance: PROMPTPurify, licensed under MIT, provides an ai-safety solution with a focus on jailbreak-detection and prompt-injection-protection for LLM applications without relying on regex or signatures.
Good fit when
- Unverified catalog guidance: - When you require compact model solutions that outperform larger open-source guards.
- Unverified catalog guidance: - If your application demands prompt-injection detection, especially in contexts where AI security is paramount like in CTF events.
Avoid when
- Unverified catalog guidance: - Avoid using PROMPTPurify if your project requires regex or signature-based methods for security purposes, as this tool does not support them.
- Unverified catalog guidance: - Do not use it if you are looking for comprehensive AI-security solutions that extend beyond prompt injection and jailbreak detection.
- Pricing:
- freemium - The SDK and model weights of PROMPTPurify come under the MIT license, allowing free usage. However, the full extent of features or services might require a premium setup.
- Requirements:
- - This tool is built with TypeScript.; - Ensure familiarity with TypeScript for efficient integration.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (80) are secondary evidence.
- npm downloads (30d)
- 99·npm downloads API·Oct 22, 2026
Maintenance and security
Full trust report- Maintenance
- Slowing (143d since push)
- As of Oct 22, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 22, 2026
- Security (OSV)
- 2 low
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
Package installation is not established from the available documentation. Check the source repository for setup instructions.
git clone https://github.com/securelayer7/promptpurifySource repositorySimilar 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
Provides an ai-safety solution focusing on jailbreak-detection and prompt-injection-protection for llm-guardrails.
Capability facts
- MCP server
- Unknown; MCP server not established by this scan
Source: repo_scan · Oct 22, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Oct 22, 2026
Categories
Tags
README
License MIT for the SDK and the model weights. Benchmark sources we evaluate against are listed in training/CORPUS LICENSES.json. Security disclosures: SECURITY.md.
For agents
This page has a .md twin and JSON over the API.