Cantina agents are reasoning systems that work across your whole stack, taking each issue from raw signal through to validated remediation. Start from a prebuilt agent, adapt one to your environment, or build your own.
Agent roster · 18 prebuilt
A Cantina agent does the work of a security analyst, not the scripted steps of a bot or workflow. It reads each issue, reasons across every system you've connected to decide whether it's real, and then acts to resolve it, bringing in a person only when the situation genuinely calls for one.
Every skill is readable. Start with a prebuilt agent, fork the one that's closest, or build your own from scratch.
Monitors
01 / 18GCP Security Command Center
active · last run 2026-06-30
Catches posture drift such as public buckets and over-permissive IAM, grades it by real data sensitivity and usage, and shuts it down before it's abused.
Consequential changes route through human approval.
Monitors
02 / 18Okta + Google Workspace
active · last run 2026-06-30
The account-takeover specialist. Correlates device, network, and posture signals to kill false-positive pages before it suspends anyone.
Monitors
03 / 18CrowdStrike Falcon
active · last run 2026-06-30
The host-containment specialist: confirm true-positive, isolate fast, stopping C2 while keeping the box up for forensics.
Monitors
04 / 18Apex code findings
active · last run 2026-06-30
The code-and-secrets specialist, built to cut CVE noise by proving real exposure through reachability instead of scanner hits.
Monitors
05 / 18Cantina BBP
active · last run 2026-06-30
The external-report validator. Grounds every inbound claim in your real code and live cloud config before anyone spends time on it.
Monitors
06 / 18RSS feed
monitor inactive
The noise filter for external intel surfaces only what touches your stack, retro-hunts named CVEs against your assets, and suppresses the rest.
Monitors
07 / 18On-chain activity
available
Monitors on-chain threats and suspicious activity, with emergency pause when contracts are compromised.
Monitors
08 / 18Identity providers
recommended
Investigates suspicious logins, MFA issues, account compromise, and risky OAuth across identity providers.
Monitors
09 / 18GCP audit logs + SCC + Cloud Monitoring
recommended
Reviews GCP audit logs, Security Command Center findings, and Cloud Monitoring incidents for privilege abuse, credential theft, exposures, and service risk.
Monitors
10 / 18AWS CloudTrail + GuardDuty
recommended
Monitors AWS through CloudTrail and GuardDuty for IAM, compute, logging, and exposure risks.
Monitors
11 / 18GitHub
recommended
Finds secrets, scan failures, branch protection gaps, and repository visibility issues in GitHub.
Monitors
12 / 18DNS + email authentication
available
Monitors DNS and email-auth changes, new subdomains, and takeover risk.
Monitors
13 / 18Advisories + IOCs + threat intel
available
Correlates advisories, indicators of compromise, and threat intelligence to your environment.
Monitors
14 / 18Clarion integration health
available
Provides supplemental repair triage for Clarion integration and monitor health issues.
Monitors
15 / 18Signal rule performance
available
Reviews how your signal rules perform and proposes tuning to cut noise and close detection gaps.
Monitors
16 / 18SIG + DDQ + VSA + CAIQ
available
Drafts grounded answers and gathers supporting evidence for inbound third-party security questionnaires.
Monitors
17 / 18Connected workspace sources
available
Owns periodic ingestion of connected sources into the workspace Brain and holds the editorial policy for extracted knowledge. Deactivate it to pause knowledge-feed runs across the workspace.
Monitors
18 / 18Defender for Cloud + Entra ID + Azure RBAC
available
Monitors Defender for Cloud alerts, Entra ID and RBAC privilege abuse, storage and Key Vault exposure, network and compute compromise, defense evasion, and misconfiguration remediation.
Connect your tools and prebuilt agents cover your security surface from day one.
Fork a default and make it yours.
Most teams take the default that's closest to what they need and adjust its logic, thresholds, and workflow until it fits their environment.
Fully programmable agents, built from skills, playbooks, and tools.
When you need something specific, build an agent from the ground up: compose its skills, connect each one to only the tools it needs, and orchestrate complete workflows across your systems.
An agent proven and shared from the Cantina Customer Community.
Bring in an agent another team has already proven, with its skills and thresholds intact, then connect your own tools and set your own level of autonomy. Because every skill is readable, you can see exactly what it does before it runs.
Cantina agents close issues, contain hosts, and change configurations. You decide what they can do, how much runs on its own, and see exactly what happened.
Available now. Cantina finds, scores, and drafts the fix. You approve every action. Full control, full visibility, proof on every call.
Agents watch 4 domains
Reachability + risk
Contain, fix, rotate
Merged + re-tested
Start prebuilt, adapt it, or build your own. Either way, you're directing agents, not chasing alerts.
