ralph-wiggum-loop@r1
CAUTION· install onlyPublisher claims: "Enables an autonomous multi-model iterative development loop where a worker model implements changes and a reviewer model evaluates them, iterating until a SHIP decision is reached." 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: 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; 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.
Is ralph-wiggum-loop@r1 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 2026-11-15 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe to network utility; Privileged sudo command; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
chmod +x ./bin/script-runner ./bin/script-runner.sh ./bin/package-mcpb.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.handle_http_request_stream < "${_mshs_fifo}" | nc -l "${_mshs_host}" "${_mshs_port}" > "${_mshs_fifo}" || breakFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.npx skills add sheldonrobinson/ralph-wiggum-loopFix: Pin versions and sources; vendor anything fetched at install time.if [ -n "${pid}" ] && kill -0 "${pid}" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- **Via Skill Installers (`npx skills` / `openskills`):**Fix: Pin versions and sources; vendor anything fetched at install time.kill "${MCP_HTTP_SERVER_PID}" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "${running_pid}" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x /usr/local/bin/mcp-publisherFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.echo "Install with: brew install socat (macOS) or sudo apt-get install -y socat (Linux)" >&2Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- Ubuntu/Debian: `sudo apt-get install -y jq socat`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "${MCP_HTTP_SERVER_PID}" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x "${STAGE_SH}/bin/ralph-wiggum-loop.sh" "${STAGE_SH}/bin/mcp-sdk.sh" "${STAGE_SH}/bin/script-runner" "${STAGE_SH}/bin/script-runner.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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.
What would make this Verified
11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe to network utility≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim sheldonrobinson: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.