Skills/ClawHub/jf-open-pro-watchdog

jf-open-pro-watchdog@1.0.1

VERIFIED

Publisher claims: "杰峰看门狗技能。基于杰峰设备抓图 + AI 视觉分析的通用区域状态监控，支持物品防盗、通道占用检测、人员存在检测等场景。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jftech · joined 0 days agoInstalls 571Last detonated 2 h ago
$clawhub install jf-open-pro-watchdog
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-29 and scored it 90/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

MEDIUM
File type combined with upload actionSKILL.md:576 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:581 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:669 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07