A Kubernetes control plane for fleets of conformant AI agents. agentctl provisions, configures (intelligence, tools, instructions), scales, observes, secures, and exposes agents — declaratively, through Custom Resources.
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- B · 21 → A · 9
- B · 29 → B · 21
- B · 21 → B · 29
No known CVEs for this server.
- high dangerous code
committed secret: private key, Slack token
analyzed commit 1bd40b2 · analyzer v33 · 2w ago
danger signals2
- committed secret private key AgentCTL-dev-source-code-1bd40b2/crates/agentctl-gateway/src/oidc.rs :403
PEM private key block (redacted) - committed secret Slack token AgentCTL-dev-source-code-1bd40b2/docs/use-cases.md :62
xoxb-y…(27 chars, redacted)
[](https://mcpobservatory.com/servers/github:AgentCTL-dev/source-code/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of AgentCTL-dev.