Launched this week
Your AI agent runs third-party skills and MCP servers with full access to your files, keys and shell — no sandbox, no review. I scanned 96,096 published skills; 751 were malicious. PanGuard vets a skill before you install it, scans what you already have, and blocks hijack attempts at runtime. Free, MIT, fully on-device. Powered by 768 open ATR rules, already merged into Microsoft, Cisco, MISP and OWASP tooling. One command: npm install -g panguard && pga up
ran the scan against a few skills i had sitting around and it flagged one i would have totally missed. love that it just runs locally without sending anything off-box.
Ran the install in under a minute and it immediately flagged two skills I'd been using for months as sketchy. Wild that something this thorough is free and on-device.
751 out of 96k is a much higher malicious rate than I expected, that's a genuinely useful number to have public. for the runtime hijack blocking specifically, is that based on known attack signatures or are you also catching novel prompt-injection-style hijacks that don't match an existing rule yet?
solo builder, self-taught, four months in, and already merged into Microsoft/Cisco/MISP/OWASP tooling is a wild pace. one question on the runtime watcher piece specifically, does watching the agent at runtime add any noticeable latency to its actual work, or is it lightweight enough to just leave running in the background all the time
love that you put real numbers out there instead of hand-wavy claims, the 751 out of 96096 figure is the kind of evidence that makes this feel like a serious tool rather than a pitch. shipping it open source with the ATR rules already folded into MISP and OWASP is genuinely impressive execution.
@zzetcanla2en love you to man ,the 751 needs an asterisk. it was a snapshot, registry had moved by the next morning, so treat it as a floor not a census.
and the numbers split by corpus rather than being one figure. on the skill corpus the pattern layer does well, on prompt injection specifically (PINT, 850 samples) it only gets 63.6%. that gap is the reason there's a runtime guard and not just a scanner.
ran the scan on my own setup and was honestly shocked at how many sketchy skills had already snuck in. the one command setup made it painless.
@seldao4xu That's the part most people don't expect. You don't install anything obviously sketchy
it just accumulates, often pulled in as a dependency of something else, and nothing ever prompts you.
If any of them look like false positives, tell me.
Over-eager rules are worth more to me right now than praise.
Every rule is public YAML, so a bad one gets fixed in the open.
Macaly
751 malicous skills out of 96k is genuinely scary 😅 runtime guard for agents is so needed. congrats 👏
@petrkovacik thanks man, keep grinding