relaywright@0.1.0-rc.3
VERIFIED· install onlyPublisher claims: "Enables an AI agent to learn a Chromium browser task once and then replay it deterministically without spending LLM tokens, handing off logins and CAPTCHAs to a human while keeping credentials out of the model. Every step is de-identified for privacy and written to a hash-chained audit log, available as both an MCP server and a CLI." 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
DEEPSEEK_API_KEYConfiguration, not credentials: ProgramFiles, ProgramW6432, RELAYWRIGHT_BROWSER, RELAYWRIGHT_CHROME, RELAYWRIGHT_EVAL, RELAYWRIGHT_HEADLESS, RELAYWRIGHT_HOME, RELAYWRIGHT_NOTIFY, RELAYWRIGHT_PRIVACY, RELAYWRIGHT_TEST_ACCESS_DECISION, RELAYWRIGHT_TEST_ADOPT_DECISION, TERM_PROGRAM, VITEST, VSCODE_GIT_ASKPASS_MAIN, VSCODE_GIT_ASKPASS_NODE- Where it talks to
- no vendor host named in the codeAlso deepseek.com, example.edu — 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
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names deepseek.com, example.edu as well as its own vendor. The guard injects DEEPSEEK_API_KEY 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 91/100 (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
const SPACE = /[\t\n\r\f\v\u00a0\u1680\u2000-\u200a\u2028\u2029\u202f\u205f\u3000\ufeff]+/g;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.No other findings across 22,049 lines in 81 files.
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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.