Skills/ClawHub/claude-code-team-scaffold

claude-code-team-scaffold@1.0.0

VERIFIED· install only

Publisher claims: "该指令用于在 Claude Code 新项目初始化多智能体 AI 开发框架：生成.claude 目录、含 6 类生命周期钩子的配置、子智能体、斜杠命令与文件规划技能，搭建规范目录、两级记忆体系，配套代码质检、文档同步、任务流水线；触发短语含中英多组。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher lrh07819 · publishing for 141 daysInstalls 383Last detonated 2d ago
$clawhub install claude-code-team-scaffold
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.0sprocessno install scripts to re-run

Static findings

HIGH
Instructs the agent to modify its persistent memory or instruction filestemplates/commands/run-task.md:29 · Instructs the agent to modify its persistent memory or instruction files- Instruction to update the module's `CLAUDE.md` if functionality changesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestemplates/hooks/agent-stop.js:49 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file`Update module CLAUDE.md to reflect changes before stopping.\n` +Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestemplates/hooks/post-tool-use.js:84 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileprocess.stdout.write(`[soft reminder] Created ${filePath} in ${parent.replace(/\\/g, '/')} with no CLAUDE.md.\n`);Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:50 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file**Other Properties Related to Output:** [Produces project scaffolding and may write both repository-local .claude files and global ~/.claude memory or CLAUDE.md content when used as designed.]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestemplates/hooks/post-tool-use.js:78 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// Soft reminder for Write into a module root with no CLAUDE.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈2,395 tok
2 files · 35 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

claude-code-team-scaffold@1.0.0 safety verdict: Verified (install only) — KillerSkills