Shiplight MCP server for AI-powered test automation
- capability exposure inferred + 6
- tool safety inferred + 5
- trust mitigators mixed − 16
These factors total -5, not 0: the score is bounded to 0–100 after they are summed, so this one is floored at 0. The factors are left as they were applied rather than rewritten to make the column add up.
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 1w ago · see ecosystem CVEs →
- A · 5 → A · 0
- A · 10 → A · 5
- A · 4 → A · 10
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed v0.2.1 · analyzer v33 · 4w ago
danger signals2
- dynamic code execution new Function() package/dist/index.js :4112
=await e.evaluate(({code:m,argsObj:v})=>new Function("return "+m)()(v),{code:this.jsCode,argsObj:w})}let p=Object.entries(c.map).filter(([,w])=>w.tagName==="iframe");u.debug(`\u{1F50D} [ext-iframe] To - suspicious endpoint us.i.posthog.com (telemetry)
expected for this server's purpose
package/dist/index.js :4987
wJWX9qZqyRka5Lann5ATsg3LL4uyU63qin",Lf="https://us.i.posthog.com",Df=process.env.SHIPLIGHT_TELEMETRY==="0"||process.env.DO_NOT_TRACK==="1",Ka=null,Zu=!1});var nh={};Ve(nh,{startServer:()=>Kf});import{
[](https://mcpobservatory.com/servers/npm:@shiplightai/mcp/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 feng_shiplite.