detect-task@1.0.26
VERIFIEDPublisher claims: "投前 AI 图真实性质检。待检图 → 风险等级 + 8 项逐条判定 + 可直接追加到 prompt 的修正句，可自动重跑直到达标。当用户说「投前检测」「图片质检」「检查有没有崩」「上架前把关」「这图能不能用」时使用。" 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 2026-10-26 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 · 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
Fake instruction boundary tagreferences/provider-cli.md:130 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagSKILL.md:209 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagreferences/model-flags.md:13 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
npx invocation of non-well-known packagescripts/brand.mjs:97 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06