apick-mcp@5.0.0
VERIFIEDPublisher claims: "APICK MCP — 175 Korean data, AI, image & video tools for AI agents. 사업자조회·신분증·OCR·배송조회·차량제원·이미지 생성·편집·영상 생성·파일변환·검색·LLM." 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 (2 scenarios) on 2026-10-28 and scored it 88/100 (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 · 2 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
2.1sprocessexec /usr/bin/timeout
2.1sclaimed185 tools: transfer_1won, account_realname, bank_code, identi_card1, identi_card2, identi_card3, identi_card4, identi_card5, identi_card_image1, identi_card_image2, identi_card_image3, identi_card_image4, identi_card_image5, name_rrn_auth, hide_rrn, identity_document_residence_card, identity_document_passport, identity_document_id_card, identity_document_driver_license, ocr, ocr_identi1, ocr_identi2, ocr_identi3, ocr_identi4, ocr_identi5
2.1sprocessscript backend runs setup only
Static findings
CRITICAL
Fake instruction boundary tagTOOLS.md:112 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagTOOLS.md:90 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagTOOLS.md:70 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01