flintrail@1.3.0
CAUTION· startup onlyPublisher claims: "Enables AI agents to drive a real Chrome, record browser tasks once, replay them at browser speed without an LLM, and replay a site's own API calls using the existing session." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: 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
FLINTRAIL_PASSWORDSFLINTRAIL_TOKENConfiguration, not credentials: FLINTRAIL_ALLOW_ANY_BROWSER, FLINTRAIL_CDP_URL, FLINTRAIL_CHROME, FLINTRAIL_DOWNLOADS, FLINTRAIL_EXTENSION_WAIT, FLINTRAIL_HEADLESS, FLINTRAIL_HOME, FLINTRAIL_MODE, FLINTRAIL_PORT, FLINTRAIL_PROFILE, FLINTRAIL_RELAY_PORT, FLINTRAIL_URL, NO_UPDATE_NOTIFIER, RUNS, SOFLUTION_AUTO_UPDATE, SOFLUTION_FIRST_CHECK_MS, SOFLUTION_REGISTRY, SOFLUTION_SUPERVISED- Where it talks to
- no vendor host named in the codeAlso shop.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
- 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 shop.example as well as its own vendor. The guard injects FLINTRAIL_PASSWORDS, FLINTRAIL_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-14 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 25 s · 2 scenarios · 0 deviationsStatic findings
if (!token) { await setStatus('idle', 'Paste the token from ~/.flintrail/token'); return; }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…onltd/flintrail/releases/latest), unzip it, open `chrome://extensions`, enable *Developer mode*, click *Load unpacked* and pick the folder. (Chrome Web Store listing in progr…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.`The Flintrail extension is not connected. Open it in your browser, paste the token from ${config.home}/token and click Connect.`)), ms);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Everyone installed with `npx -y <package>@latest` or with the .mcpb extension then updates on their own.Fix: Pin versions and sources; vendor anything fetched at install time.…onltd/flintrail/releases/latest), unzip it, open `chrome://extensions`, enable *Developer mode*, click *Load unpacked* and pick the folder. (Chrome Web Store listing in progr…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.run(`npx -y @anthropic-ai/mcpb@2 validate "${join(out, 'manifest.json')}"`);Fix: Pin versions and sources; vendor anything fetched at install time.- run: npx playwright-core install --with-deps chromiumFix: Pin versions and sources; vendor anything fetched at install time.run(`npx -y @anthropic-ai/mcpb@2 pack "${out}" "${join(root, file)}"`);Fix: Pin versions and sources; vendor anything fetched at install time.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim soflutionltd: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.