Skills/npm/react-native-ai-debugger

react-native-ai-debugger@2.27.1

VERIFIED· startup only

Publisher claims: "React Native AI debugger: MCP server giving AI agents eyes and hands in your running app (logs, network, state inspection, tap, screenshot). Published as ExecBro." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher igorzheludkov · publishing for 329 daysInstalls 12,731Last detonated 5 h ago
$claude mcp add react-native-ai-debugger -- npx -y react-native-ai-debugger
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

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
SECRET_KEYConfiguration, not credentials: ANDROID_HOME, ANDROID_SDK_ROOT, AXE_PATH, EASYOCR_LANGUAGES, EXECBRO_API_URL, EXECBRO_CHROMIUM_PORTS, EXECBRO_REDACT, EXECBRO_TELEMETRY, EXECBRO_TEST_MODE, IDB_PATH, IOS_DRIVER, JEST_WORKER_ID, LOOSE_KEY, MAX_PATTERN_LENGTH, MCP_HTTP_PORT, RN_AI_DEVTOOLS_TEST_MODE, RN_DEBUGGER_TELEMETRY, VALID_KEY_NAMES
Where it talks to
execbro.com (its own)Also workers.dev, android.com, example.comhttps, acme.io, posthog.com — 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
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names workers.dev, android.com, example.comhttps, acme.io, posthog.com as well as its own vendor. The guard injects SECRET_KEY only into requests to execbro.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets SECRET_KEY=execbro.com -- npx -y react-native-ai-debugger

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

What changed since 2.23.0

vet-skills diff react-native-ai-debugger 2.23.0 2.27.1

In the sandbox, this version reached for nothing 2.23.0 did not. Compared from the two recorded runs, not from source.

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; startup only; authenticated tool behavior not tested) on 2026-11-19 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 · 33 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
13sprocessdependency install exit 0
33sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-sDKveV/task/home/work/acme-api/.claude/skills/react-native-ai-debugger/build/core/serialQueue.js' } Node.js v22.23.5
33sprocessscript backend runs setup only
33sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandbuild/core/exec.js:44 · Process kill command — agent can terminate processesconst kill = () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbuild/core/exec.js:11 · Process kill command — agent can terminate processesconst kill = () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbuild/core/guides.js:26 · Process kill command — agent can terminate processes- ios_terminate_app — kill an app that is in a bad state before relaunching (simulator or USB iPhone)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandpackage.json:12 · File permission modification command — agent changes file ownership/permissions"build": "tsc && chmod 755 build/bin.js build/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Prompt injectionREADME.md:129 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…mounted developer disk image; taps also need iOS 27+, pymobiledevice3 11.32.0+, Developer Mode and the Xcode 27 disk image. See [physical iOS setup](docs/setup.md#physical-io…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:129 · Authorization escalation language · informational: not an instruction file…mounted developer disk image; taps also need iOS 27+, pymobiledevice3 11.32.0+, Developer Mode and the Xcode 27 disk image. See [physical iOS setup](docs/setup.md#physical-io…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandbuild/core/ios.js:86 · Privileged sudo command — agent may execute with elevated privileges"xcode-select -p should print .../Xcode.app/Contents/Developer (fix with sudo xcode-select -s /Applications/Xcode.app).";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebuild/bin.js:19 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add execbro --scope project -- npx -y execbro@latestFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandbuild/core/ios.js:171 · Privileged sudo command — agent may execute with elevated privileges"and run `sudo xcode-select -s /Applications/Xcode.app/Contents/Developer`. " +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈83 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for react-native-ai-debugger@2.27.1 as of 4 h ago. This is the package itself, not its dependencies.

react-native-ai-debugger@2.27.1 safety verdict: Verified (startup only) — KillerSkills