GitHub Repository

🛡️ Promptinel is a deterministic security scanner for machine-interpreted natural language that treats prompts as executable artifacts.

10 starsGo

Promptinel – A Security Scanner for Prompts

Name: Promptinel – A Security Scanner for Prompts
Availability: InStock
Author: cunningfatalist

by cunningfatalist·Mar 8, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainZero to OneSolve My Problem

Deterministic prompt linter flags injection, exfiltration, obfuscation before LLM runs—treats prompts as executable code.

Strengths

•Novel framing: prompts ARE executable code, so treat them as such with static analysis + linting—this is genuinely not obvious.
•Deterministic scanner (no network, no ML model calls) means output is reproducible and automatable in CI pipelines.
•Concrete attack patterns: prompt override, role spoofing, download-and-execute chains, Unicode obfuscation, secret exfiltration intent.

Weaknesses

•Early-stage: 8 stars, 2 open issues; unclear how effective rules are at catching real-world attacks vs. false positives.
•Limited ecosystem: only scans text files; no IDE integration, no GitHub Actions pre-built yet, minimal adoption signal.

Post Description

Hello HN :)

Promptinel is a security scanner for prompts. I think the world needs something like this, because prompts are basically executable artifacts and we need to treat them as such. I want to identify as many bad things as I can before a prompt gets anywhere near runtime. Especially when supplying a common prompt repository for friends or colleagues, or when downloading skills from the internet. You can read more about my motivation in the project's readme: https://github.com/CunningFatalist/promptinel?tab=readme-ov-...

Promptinel finds various attack patterns in prompts, for example:

- prompt override and role spoofing patterns - download-and-execute chains - template execution and network fetch behavior - secret exfiltration intent - invisible Unicode and obfuscation tricks - local sensitive file references

I'm really looking forward to feedback from people, who have built linters or security scanners before. Or just feedback from Go people, really. I'm mainly a PHP and TypeScript dev and use Go in my free time, because I find it fun and love the philosophy behind it.

Similar Projects

Security●●Solid

PromptSonar – Static analysis for LLM prompt security

Static scanner catches prompt injections in code before runtime, unlike runtime guards.

Solve My ProblemShip It

meghal86

103mo ago

Security○Pass

Security-Risk Patterns in OpenClaw Skills

It actually looks for the weird stuff that trips up LLM agents — invisible Unicode, bidi overrides, embedded curl|bash one-liners, exfil links — and pairs a static skill scanner with a real-time interception flow that forces human approvals. The CLI-first approach (npx safeclaw start) plus Socket.IO alerts and per-command allow/deny decisions show practical thinking about developer workflows; I want to see model/false-positive metrics and enterprise integration docs next.

Niche GemWizardry

dinodrv

203mo ago

Security●●●Banger