Skills/npm/sheleg-design-skill

sheleg-design-skill@1.66.6

VERIFIED· install only

Publisher claims: "Design taste as an installable agent skill. Cinematic scroll-driven landing pages built on one scroll clock and layered degrade-to-calm motion, a motion doctrine that decides whether to animate before it decides how, three calibration dials, and thirty-ni" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ssheleg · publishing for 156 daysInstalls 2,390Last detonated 2d ago
$claude mcp add sheleg-design-skill -- npx -y sheleg-design-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

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 2026-11-12 and scored it 80/100 (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

MEDIUM
npx invocation of non-well-known packagebin/lint.js:7 · npx invocation of non-well-known package — may execute untrusted code* npx sheleg-design-skill --self-testFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/cli.js:319 · npx invocation of non-well-known package — may execute untrusted codenpx sheleg-design-skill [options]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/record.js:333 · npx invocation of non-well-known package — may execute untrusted code"## Markers", "npx sheleg-design-skill --lint src @ 3f2a9c1 — 0 S1, 1 S2, 0 S3",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/cli.js:515 · npx invocation of non-well-known package — may execute untrusted code// per member (npx installers share no lib): a host's config root is an explicitFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/cli.js:561 · npx invocation of non-well-known package — may execute untrusted code* 2026-08-29: a bare `npx @ssheleg/telegram-dev` shipped three shadows past aFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationbin/cli.js:698 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// with its family, and per-marketplace autoUpdate moves each member on itsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/lint.js:6 · npx invocation of non-well-known package — may execute untrusted code* npx sheleg-design-skill --lint <dir> [--json] [--ratchet <budget.json>] [--include-tests]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/cli.js:588 · npx invocation of non-well-known package — may execute untrusted code` ${c("bold", "npx --yes sshlg-skills@latest update")}\n` +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:331 · HTML comment carrying imperative instructions to the agentcommands-run-in: a cloneFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Auto-update or dynamic fetch configurationbin/cli.js:697 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// complete sentence. Auto-update is off on purpose: this member composesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/record.js:6 · npx invocation of non-well-known package — may execute untrusted code* npx sheleg-design-skill --check-record <file> [--json]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Rule modification attemptCHANGELOG.md:3748 · Rule modification attempt — overwriting existing instructions · informational: not an instruction filerule 3: the reference declares an amber in its theme layer and never paints aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagebin/cli.js:701 · npx invocation of non-well-known package — may execute untrusted code`Updates: rerun ${c("bold", "npx sheleg-design-skill@latest --force")}, or refresh the\n` +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈94 tok
1 file · 81 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 sheleg-design-skill@1.66.6 as of 2d ago. This is the package itself, not its dependencies.