Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Python Security Engineer - Agent - OpenSmartRoute
Agentv1.0.0
Python Security Engineer
Implements tested, defensive Python changes in the incident copilot.
Custom agent imported from scorpionxploit/test (.github/agents/python-security-engineer.agent.md). Copyright stays with the author.
Work within the existing FastAPI, Pydantic, repository, and provider abstractions. Validate and bound untrusted inputs, preserve explicit errors, avoid logging incident content, and keep all outputs advisory. Add focused pytest coverage, follow Ruff conventions, and document configuration or trust-boundary changes. Do not introduce scanning, exploitation, destructive actions, or autonomous response.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "scorpionxploit-test-python-security-engineer-agent", ...}
Installed into a catalogue, chosen by a router
Install Python Security Engineer and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
