cd /news/ai-safety/show-hn-intrusive-ai-open-source-ai-… · home › topics › ai-safety › article
[ARTICLE · art-172086] src=intrusive.ai ↗ pub= topic=ai-safety verified=true sentiment=↑ positive

Show HN: Intrusive.ai – open-source AI attack simulation

A developer released INTRUSIVE.AI, an open-source platform for testing AI agents against OWASP's Top 10 for Agentic Applications in non-production environments. The platform includes Interceptor Sandbox, which intercepts services such as HTTP, MCP and Postgres/pgvector via an injection API to deliver malicious payloads for indirect prompt injection testing, plus Attack Harness and Operator Sandbox for running untrusted attack tooling. The developer describes the suite as alpha-stage and is soliciting feedback through GitHub Issues on the interceptor_sandbox and operator_sandbox repositories.

key takeaway

Interceptor Sandbox lets builders intercept HTTP, MCP and Postgres/pgvector calls via an injection API to plant malicious payloads, enabling indirect prompt injection tests against OWASP's Top 10 for Agentic Applications without touching production.

read1 min views5 publishedNov 18, 2026

I created the INTRUSIVE.AI platform to give agent builders the ability to evaluate their agents against OWASP's Top 10 for Agentic Applications (and more generally, just to allow for comprehensive testing in a non-production environment).

Through my own experience with evaluating agents, I found indirect prompt injection testing to be especially difficult due to the architectural nature of it. To overcome that challenge, I created Interceptor Sandbox - a sandbox that runs agents in a simulated environment where all of the services an agent might rely on (HTTP, MCP, Postgres/pgvector to name a few) can be "intercepted" via an injection API to inject malicious payloads.

Interceptor Sandbox:

https://github.com/intrusiveai/interceptor_sandbox Additionally, I found that existing open source AI testing and attack simulation solutions didn't provide the breadth of capabilities I needed so I created Attack Harness for that purpose. But it also had to be sandboxed because any sufficiently capable attack harness can't be trusted to play nice once it's been given nefarious goals and so that led to Operator Sandbox. I haven't seen other people talking about the sandboxing method that I've employed in Operator so it seems to be a somewhat novel approach that might shake up the way people are thinking about sandboxing AI agents.

Operator Sandbox:

https://github.com/intrusiveai/operator_sandbox The full suite is documented here:

https://docs.intrusive.ai The platform is still very much in its alpha stage so your mileage may vary but I would sure appreciate any feedback that comes my way. Feel free to use GitHub Issues on the respective repos to provide feedback.

Comments URL: [https://news.ycombinator.com/item?id=50550896](https://news.ycombinator.com/item?id=50550896)

Points: 1

── more in #ai-safety 4 stories · sorted by recency
── more on @intrusive.ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-intrusive-ai…] indexed:0 read:1min 2026-11-18 · —