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.
cloud-defense - Skill - OpenSmartRoute
Skillv1.0.0
cloud-defense
Detect and break the cloud post-compromise attack chain (AWS / Azure / GCP) — per-stage CloudTrail / Activity-Log / Audit-Log detection signals and the preventive controls that close each step.
Imported from transilienceai/communitytools (skills/cloud-defense/SKILL.md). Install upstream with npx skills add transilienceai/communitytools --skill cloud-defense. Copyright stays with the author.
Cloud Defense
The blue-team counterpart to cloud-containers. For each attacker move — lateral movement, privilege escalation, data exfiltration, defense evasion — this skill gives the log event to alert on and the single control that removes the technique. Use it to turn an offensive cloud finding into a concrete detection and remediation.
When to use
Writing the remediation / hardening section of a cloud pentest report.
Cloud detection engineering: deciding which control-plane events to alert on.
Reviewing an AWS / Azure / GCP account's posture against the post-compromise chain.
Workflow
Confirm the logging prerequisites are in place (org-wide trail, data events, threat detection on) — without them the signals below are invisible.
Copy one of these into your project. Installing also returns the manifest and these snippets.
Installed into a catalogue, chosen by a router
Install cloud-defense 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.
When a provider is down or over quota the request moves on; the trace says it did.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "transilienceai-communitytools-cloud-defense",
"kind": "skill",
"name": "cloud-defense",
"description": "Detect and break the cloud post-compromise attack chain (AWS / Azure / GCP) — per-stage CloudTrail / Activity-Log / Audit-Log detection signals and the preventive controls that close each step. Use for cloud detection engineering, hardening, remediation write-ups, or blue-team posture review of the lateral-movement -> privilege-escalation -> exfiltration -> evasion chain.",
"publisher": "transilienceai",
"version": "1.0.0",
"capabilities": {
"domains": [
"observability"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Detect and break the cloud post-compromise attack chain (AWS / Azure / GCP) — per-stage CloudTrail / Activity-Log / Audit-Log detection signals and the preventive controls that close each step. Use for cloud detection engineering, hardening, remediation write-ups, or blue-team posture review of the lateral-movement -> privilege-escalation -> exfiltration -> evasion chain."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/transilienceai/communitytools",
"path": "skills/cloud-defense/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/transilienceai/communitytools/blob/HEAD/skills/cloud-defense/SKILL.md",
"key": "transilienceai/communitytools/skills/cloud-defense/SKILL.md"
}
},
"instructions": "# Cloud Defense\n\nThe blue-team counterpart to [`cloud-containers`](../cloud-containers/SKILL.md). For each attacker move — lateral movement, privilege escalation, data exfiltration, defense evasion — this skill gives the log event to alert on and the single control that removes the technique. Use it to turn an offensive cloud finding into a concrete detection and remediation.\n\n## When to use\n\n- Writing the remediation / hardening section of a cloud pentest report.\n- Cloud detection engineering: deciding which control-plane events to alert on.\n- Reviewing an AWS / Azure / GCP account's posture against the post-compromise chain.\n\n## Workflow\n\n1. Confirm the logging prerequisites are in place (org-wide trail, data events, threat detection on) — without them the signals below are invisible.\n2. Map each attacker stage to its detection signal — see [reference/detection-signals.md](reference/detection-signals.md).\n3. Apply the preventive control that breaks each stage — see [reference/hardening-controls.md](reference/hardening-controls.md).\n4. Re-run the matching offensive technique from [`cloud-containers`](../cloud-containers/SKILL.md) to confirm the control holds or the alert fires.\n\n## References\n\n- [reference/INDEX.md](reference/INDEX.md) — router\n- [reference/detection-signals.md](reference/detection-signals.md) — per-stage log signals + logging prerequisites\n- [reference/hardening-controls.md](reference/hardening-controls.md) — the control that breaks each stage",
"cost": {
"context_tokens": 371
}
}
Fetch it by URL: GET /api/v1/registry/transilienceai-communitytools-cloud-defense/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.