ai-design-check@0.10.0
VERIFIEDPublisher claims: "Finds and fixes what makes AI-built interfaces look generated, on the web and in SwiftUI and Jetpack Compose apps: 87 design rules, a zero-dependency checker, a design system generator (fonts, type, colours that pass contrast), an agent fix skill and befo" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-02 and scored it 81/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
CRITICAL
Prompt injectionRULES.tr.md:333 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
npx invocation of non-well-known packagebin/ai-design-check.js:12 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06CRITICAL
Prompt injectionREADME.tr.md:107 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.tr.md:72 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionrules.json:2028 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionrules.json:780 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionRULES.tr.md:203 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionrules.json:788 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionRULES.tr.md:209 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
npx invocation of non-well-known packageskills/design/SKILL.md:12 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/story.js:264 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design-fix/SKILL.md:119 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design-fix/SKILL.md:56 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design-fix/SKILL.md:108 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebin/ai-design-check.js:13 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/system.js:35 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebin/ai-design-check.js:14 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebin/ai-design-check.js:15 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design-fix/SKILL.md:19 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design/SKILL.md:44 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/design/SKILL.md:19 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebin/ai-design-check.js:16 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/story.js:250 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06