Skills/npm/skill

skill@0.4.1

VERIFIED· install only

Publisher claims: "Install the free Struq skill into Claude Code, Cursor, Codex and other AI coding tools: websites at the level of a design studio, built by your own AI." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher struq · publishing for 19 daysInstalls 2,056Last detonated 8d ago
$claude mcp add skill -- npx -y @struq/skill
WatchReport an issue

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 changed since 0.3.0

vet-skills diff skill 0.3.0 0.4.1

This version reaches for something 0.3.0 did not: 2 new hosts (gstatic.com, instagram.com). Compared from the two recorded runs, not from source.

New hosts
gstatic.com, instagram.com

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 81/100 (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 · 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

HIGH
URL with embedded credentialsskills/struq/recipes/app/fonts.ts:10 · URL with embedded credentials — may be phishing or credential leaking"https://fonts.googleapis.com/css2?family=Fraunces:ital,wght@1,100..900&display=swap",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagecli/struq.mjs:34 · npx invocation of non-well-known package — may execute untrusted codenpx @struq/skill@latest remove remove the skill again (takes the same flags)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
URL with embedded credentialsskills/struq/recipes/app/fonts.ts:8 · URL with embedded credentials — may be phishing or credential leaking"https://fonts.googleapis.com/css2?family=Urbanist:[email protected]&display=swap",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagecli/struq.mjs:33 · npx invocation of non-well-known package — may execute untrusted codenpx @struq/skill@latest --project into this project instead of your home folderFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Prompt injectionskills/struq/SKILL.md:102 · Prompt injection — known jailbreak technique referenceproduct, add: "Ik heb geen foto's van je <product>: stuur ze, dan komen ze in de hero."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
URL with embedded credentialsskills/struq/recipes/app/fonts.ts:11 · URL with embedded credentials — may be phishing or credential leaking"https://fonts.googleapis.com/css2?family=Fraunces:ital@1&display=swap",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagecli/struq.mjs:31 · npx invocation of non-well-known package — may execute untrusted codenpx @struq/skill@latest install for every AI tool found on this machineFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
URL with embedded credentialsskills/struq/recipes/app/fonts.ts:6 · URL with embedded credentials — may be phishing or credential leaking"https://fonts.googleapis.com/css2?family=Fraunces:[email protected]&display=swap",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagecli/struq.mjs:32 · npx invocation of non-well-known package — may execute untrusted codenpx @struq/skill@latest --claude only for one tool: ${TOOLS.map((t) => `--${t.flag}`).join(', ')}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/struq/SKILL.md:120 · npx invocation of non-well-known package — may execute untrusted code(`npx next start -p 4321`) at 390 and 1440 and scroll it once: the preloader lands on the hero, every frame fills, eachFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detectedskills/struq/scripts/check.mjs:294 · Unicode escape sequence detected — may contain obfuscated payloadstell("Dashes", /[\u2012\u2013\u2014\u2015\u2E3A\u2E3B]|&(mdash|ndash|horbar);|&#(821[0-3]);|&#x201[2-5];/i,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagecli/struq.mjs:2 · npx invocation of non-well-known package — may execute untrusted code// npx @struq/skill@latest: copies the Struq skill into every AI coding tool found on this machine.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈3,244 tok
1 file · 80 in bundle

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

Known vulnerabilities

No advisories in OSV for @struq/skill@0.4.1 as of 8d ago. This is the package itself, not its dependencies.