agent-skill-inventory@1.5.3
VERIFIEDPublisher claims: "Office-agent skill inventory & health check. Scans any skills directory, measures size and context-token footprint, detects duplicates, and classifies skills into used / protected / closeable / manual-review buckets. Reverse-dependency scanning locks skills referenced by automations, hooks or plugins. Read-only by default: two disclosed, consent-gated writes — `--overrides --apply --yes` (programmatic close on platforms like WorkBuddy; dry-run without --yes) and `--set-lang` (saves language preference to ~/.workbuddy/skill-inventory.json) — plus one backup artifact (timestamped settings.json.bak.<ts>) created before the close write. No network, no subprocesses. English docs: SKILL.en.md. 办公型 Agent 技能库盘点与效能体检。扫描任意技能目录,统计数量/体积/上下文 token 占用,识别重复技能,按「在用/受保护/可关闭/需人工确认」四档给出建议;反向依赖扫描锁定被自动化/Hook/插件引用的技能。默认只读,两处写路径均需授权:`--overrides --apply --yes`(缺 --yes 仅预览)与 `--set-lang`(写语言偏好)。无网络、无子进程。" 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 2026-10-27 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 deviationsStatic findings
No findings across 3,024 lines in 9 files.