jabali-mcp@r1

VERIFIED· install only

Publisher claims: "Enables AI assistants to drive Jabali Panel operations such as domains, DNS, mail, applications, databases, backups, and fleet/admin tasks through natural language. It wraps the panel's REST API with read-only defaults, opt-in writes, confirmation-gated destructive actions, and dry-run support." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher shukiv · publishing for 3 daysInstalls 0Last detonated 3d ago

$npx skills add jabali-mcp

Watch Report an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.

Tested: every file read, file written and host contacted by what ran
Not tested: use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for: JABALI_API_TOKENConfiguration, not credentials: JABALI_CA_FILE, JABALI_DOCS_URL, JABALI_MCP_ADMIN, JABALI_PANEL_NAME, JABALI_PANEL_URL, JABALI_PANELS_FILE
Where it talks to: jabali-panel.com (its own)Also panel.example — not the publisher's domain; check what for before connecting.
What the honeypot saw: no credential files read · no network
What we could not test: use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names panel.example as well as its own vendor. The guard injects JABALI_API_TOKEN only into requests to jabali-panel.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets JABALI_API_TOKEN=jabali-panel.com -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is jabali-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

CRITICAL

HTML comment carrying imperative instructions to the agentdocs/TOOLS.md:3 · HTML comment carrying imperative instructions to the agent

Generated by cmd/gen-tools -docs from openapi/openapi.yaml + the curation files. DO NOT EDIT — run 'make docs' after changing the tool surface.

Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

MEDIUM

File permission modification commandinternal/client/registry.go:43 · File permission modification command — agent changes file ownership/permissionsreturn fmt.Errorf("chmod %s: %w", path, err)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.

AST05

Cost to the agent

Instructions loaded

≈33 tok

1 file · 41 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.