Skills/Glama/ralph-wiggum-loop

ralph-wiggum-loop@r1

CAUTION· install only

Publisher 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.

Registry GlamaPublisher sheldonrobinson · publishing for 6 daysInstalls 0Last detonated 6d ago

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.

$vet-skills run --net declared -- <the server's command>

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification command.github/workflows/publish-mcp-registry.yml:57 · File permission modification command — agent changes file ownership/permissionschmod +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.
AST05
CRITICAL
Pipe to network utilitybin/mcp-sdk.sh:702 · Pipe to network utility — potential reverse shellhandle_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.
AST05
MEDIUM
npx invocation of non-well-known packageskills/ralph-wiggum-loop/SKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codenpx skills add sheldonrobinson/ralph-wiggum-loopFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandskills/ralph-wiggum-loop/scripts/start-http-server.sh:89 · Process kill command — agent can terminate processesif [ -n "${pid}" ] && kill -0 "${pid}" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageskills/ralph-wiggum-loop/SKILL.md:37 · npx invocation of non-well-known package — may execute untrusted code- **Via Skill Installers (`npx skills` / `openskills`):**Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandbin/mcp-sdk.sh:83 · Process kill command — agent can terminate processeskill "${MCP_HTTP_SERVER_PID}" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/ralph-wiggum-loop/scripts/start-http-server.sh:149 · Process kill command — agent can terminate processeskill "${running_pid}" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification command.github/workflows/publish-mcp-registry.yml:108 · File permission modification command — agent changes file ownership/permissionschmod +x /usr/local/bin/mcp-publisherFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandskills/ralph-wiggum-loop/scripts/start-http-server.sh:116 · Privileged sudo command — agent may execute with elevated privilegesecho "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.
AST05
HIGH
Privileged sudo commandskills/ralph-wiggum-loop/SKILL.md:165 · Privileged sudo command — agent may execute with elevated privileges- Ubuntu/Debian: `sudo apt-get install -y jq socat`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbin/mcp-sdk.sh:82 · Process kill command — agent can terminate processesif kill -0 "${MCP_HTTP_SERVER_PID}" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandbin/package-mcpb.sh:214 · File permission modification command — agent changes file ownership/permissionschmod +x "${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.
AST05

Cost to the agent

Instructions loaded
≈3,367 tok
1 file · 35 in bundle

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%
  1. Pipe to network utility≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim sheldonrobinsonPropose a patch to the maintainer