desktop-driver-mcp@0.1.4
CAUTION· not startedPublisher claims: "Model Context Protocol server that exposes Desktop Driver agent operations to coding agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.1.3
vet-skills diff desktop-driver-mcp 0.1.3 0.1.4In the sandbox, this version reached for nothing 0.1.3 did not. Compared from the two recorded runs, not from source.
0.1.3 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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Text pushed off-screen by whitespace. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 6 s · 2 scenarios · 0 deviationsStatic findings
| Private `fabric-f5-ingress-bypass.json`, `fabric-f5-ingress-bypass-retry.json`, `fabric-f5-ingress-bypass-final.json`, `fabric-f5-channel-idle.json`, `fabric-Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.No other findings across 3,357 lines in 28 files.
Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim fluentui-react-native: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.