rtings-mcp@0.3.7
VERIFIED· not startedPublisher claims: "MCP server exposing RTINGS.com test data as structured tools" 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: 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
- no credential variables read in the code
- Where it talks to
- rtings.com (its own)
- What the honeypot saw
- 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 and talks to rtings.com, its own; 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 0.3.6
vet-skills diff rtings-mcp 0.3.6 0.3.7This version reaches for something 0.3.6 did not: 1 new host (rtings.com). Compared from the two recorded runs, not from source.
- New hosts
- rtings.com
0.3.6 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 2026-11-16 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 · 0 s · 2 scenarios · 0 deviationsStatic findings
# --------------------------------------------------------------------------- kill of last resortFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.f"{SESSION_COOKIE_NAME} is HttpOnly, so document.cookie cannot read it and "Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Load specific important css to override browsi stylingFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.plus a pid kill of last resort, and an `atexit` reaper for a loop torn down mid-capture.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.``_rtings_session`` is **HttpOnly**, so ``document.cookie`` cannot read it and cURL isFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.#: and SIGKILLed. 8.0 s clears the slowest seen (5.08 s) with room; the kill stays the lastFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.`document.cookie` cannot see it and a console fallback does not exist — which is why the pasteFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.and the kill fires rather than the teardown running twice as long as promised."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(_command_line_argv(pid), capture_output=True, text=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.No browser is launched. The context, browser and kill are fakes; what runs is the shippedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.turns the kill of last resort off and leaves only the graceful path."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""The sign-in window's teardown: budgets, the kill of last resort, and abandoning a hung step.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.without `force`, and without a network round-trip. Stored but unproven ⇒ **verify, do not refuseFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.render social logo override if it is providedFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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.