Skills/npm/create-vfrey

create-vfrey@1.0.0-beta.7

VERIFIED· install only

Publisher claims: "Start a vfrey project: a folder where your coding agent makes short vertical videos. Run npm create vfrey@latest my-channel." Observed in sandbox: calls registry.npmjs.org only, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher vfreyai · publishing for 27 daysInstalls 1,114Last detonated 11 min ago
$claude mcp add create-vfrey -- npx -y create-vfrey
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 1.0.0-beta.5

vet-skills diff create-vfrey 1.0.0-beta.5 1.0.0-beta.7

In the sandbox, this version reached for nothing 1.0.0-beta.5 did not. Compared from the two recorded runs, not from source.

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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 90/100 (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: calls registry.npmjs.org only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 16 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15sprocessexec /app/apps/web/node_modules/.bin/npm
15sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/npm
15sprocessexec /app/node_modules/.bin/npm
15sprocessexec /pnpm/npm
15sprocessexec /usr/local/sbin/npm
15sprocessexec /usr/local/bin/npm
15sprocessexec /tmp/ks-detonate-Jgxmk7/scripts/home/work/acme-api/.claude/skills/create-vfrey/vfrey/node_modules/esbuild/bin/esbuild
15sprocessexec /tmp/ks-detonate-Jgxmk7/scripts/home/work/acme-api/.claude/skills/create-vfrey/vfrey/node_modules/tsx/node_modules/esbuild/bin/esbuild
15sprocessexec /tmp/ks-detonate-Jgxmk7/scripts/home/work/acme-api/.claude/skills/create-vfrey/vfrey/node_modules/tsx/node_modules/@esbuild/linux-x64/bin/esbuild
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocess3 of 3 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
15sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagelib/create.mjs:172 · npx invocation of non-well-known package — may execute untrusted code? " Open the folder in your coding agent (most read the skills in .agents/skills; for Claude Code run `npx vfrey agents add claude`).\n"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagelib/create.mjs:60 · npx invocation of non-well-known package — may execute untrusted codeChange later: npx vfrey agents.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagelib/create.mjs:176 · npx invocation of non-well-known package — may execute untrusted codeconst series = seriesId ? ` Your first series is "${seriesId}": your agent reads its kit with \`npx vfrey series kit ${seriesId}\` (all ids: \`npx vfrey series list\`).\n` : "";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagelib/create.mjs:43 · npx invocation of non-well-known package — may execute untrusted codeconst USAGE = "npx create-vfrey [dir] [--name NAME] [--agent <agent>|all|none]... [--engine remotion|hyperframes|vfrey-render|vfrey-media] [--no-install] [--from DIR] [--package P] [--yes]";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈60 tok
1 file · 7 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.