Skills/ClawHub/claude-agent

claude-agent@2.1.0

VERIFIED· install only

Publisher claims: "作为项目经理操作 Claude Code 完全体。包含:任务执行(提示词设计→执行→监控→质量检查→迭代→汇报)。通过 tmux 操作交互式 CLI,通过 hooks + pane monitor 实现异步唤醒。NOT for: 简单单行编辑(用 edit)、读文件(用 read)、快速问答(直接回答)。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher n1neman · publishing for 244 daysInstalls 1,178Last detonated 29 min ago
$clawhub install claude-agent
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 2026-11-16 and scored it 89/100 (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

CRITICAL
Fake instruction boundary tagSKILL.md:86 · Fake instruction boundary tagnohup claude -p --dangerously-skip-permissions --model claude-sonnet-4-6 "<prompt>" > /tmp/claude_output.txt 2>&1 &Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagworkflows/standard_task.md:67 · Fake instruction boundary tag · informational: not an instruction filenohup claude -p --dangerously-skip-permissions --model claude-sonnet-4-6 "<prompt>" > /tmp/claude_output.txt 2>&1 &Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedhooks/on_complete.py:110 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandhooks/stop_claude.sh:12 · Process kill command — agent can terminate processeskill "$(cat "$MONITOR_PID_FILE")" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedhooks/on_complete.py:142 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,824 tok
1 file · 23 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.