roxels-mcp@0.27.0
VERIFIED· install onlyPublisher claims: "MCP server for Roxels. Let AI agents control Roxels directly: set up end-to-end AI voice conversations — webhooks, data sources, app embeds, structured-result extraction — and define each conversation's goals. Use Roxels to onboard new customers to your product or gather insights from users by letting them speak or share their screen." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
ROXELS_API_KEYConfiguration, not credentials: ROXELS_API_URL- Where it talks to
- roxels.ai (its own)
- 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. It asks for ROXELS_API_KEY and talks to roxels.ai. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.5.1
vet-skills diff roxels-mcp 0.5.1 0.27.0This version reaches for something 0.5.1 did not: 1 new host (roxels.ai) · 1 new credential variable (ROXELS_API_KEY). Compared from the two recorded runs, not from source.
- New hosts
- roxels.ai
- New credential variables
- ROXELS_API_KEY
0.5.1 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] 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 2026-11-16 and scored it 84/100 (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 deviationsStatic findings
f"Visit the submission URL to enter your secret value securely in the browser "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Bearer sk_live_realtoken12345abcdef",Fix: Never read or enumerate credential locations; accept a documented environment variable instead."sk_live_abc123def456",Fix: Never read or enumerate credential locations; accept a documented environment variable instead.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.