Skills/Glama/flow-behind

flow-behind@1.0.0

CAUTION· startup only

Publisher claims: "Enables MCP clients to generate Google Flow images and videos, check connection status, list jobs, and retrieve job results through a local browser bridge." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher behindofficial · publishing for 0 daysInstalls 0Last detonated 2 h ago

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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso nodejs.org, workers.dev — not the publisher's domain; check what for before connecting.
What we saw when it ran
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 under the guard. Startup only; authenticated tool behavior not tested. 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 [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-20 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: Privileged sudo command; Privileged sudo command; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
3.6sprocessdependency install exit 0
24sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-7WpisY/task/home/work/acme-api/.claude/skills/flow-behind-cli/dist/cli.js' } Node.js v22.23.5
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionsrc/cli.js:538 · File type combined with upload action — agent may exfiltrate local data fileselse console.log(`merged ${r.inputs} clips (${r.method}) \u2192 ${r.output}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandsrc/commands/dewatermark.js:181 · Privileged sudo command — agent may execute with elevated privilegesconst how = process.platform === "win32" ? "winget install Gyan.FFmpeg" : process.platform === "darwin" ? "brew install ffmpeg" : "sudo apt install ffmpeg (or your distribution's equivalent)";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandskills/flow-generate/SKILL.md:643 · Privileged sudo command — agent may execute with elevated privileges- Needs ffmpeg on PATH — `winget install Gyan.FFmpeg` (Windows), `brew install ffmpeg` (macOS), `sudo apt install ffmpeg` (Linux) — or set `FFMPEG_PATH`.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/cli.js:571 · File type combined with upload action — agent may exfiltrate local data fileselse console.log(`${r.mode}: ${r.detail} \u2192 ${r.output}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/flow-generate/SKILL.md:513 · Process kill command — agent can terminate processes**`stop` is the kill switch — reach for it.** A batch that is going wrong keepsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:24 · Privileged sudo command — agent may execute with elevated privilegesrun: sudo apt-get update && sudo apt-get install -y ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageskills/flow-generate/SKILL.md:651 · npx invocation of non-well-known package — may execute untrusted code`npx hyperframes@latest`. So do NOT assume it is present and do NOT install itFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/bridge/server.js:88 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`[bridge] ${msg.site}: keeping ${state.browser}, ${msg.browser ?? "?"} put on standby`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandsrc/commands/doctor.js:155 · Privileged sudo command — agent may execute with elevated privilegesconst how = platform === "win32" ? "winget install Gyan.FFmpeg" : platform === "darwin" ? "brew install ffmpeg" : "sudo apt install ffmpeg (or your distribution's equivalent)";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstest/helpers.js:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, FLOW_BEHIND_HOME: home, FLOW_BEHIND_NO_UPDATE_CHECK: '1', FLOW_AUTO_NO_UPDATE_CHECK: '1', ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈15,933 tok
1 file · 42 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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%
  1. Unclaimed publisher≈ +8 on the totalClaim behindofficial: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim behindofficialPropose a patch to the maintainer