BC claude-code-allinone
ArkClaw / OpenClaw 沙箱里一键安装并配置 Anthropic Claude Code CLI 的 all-in-one skill。当用户提到 claude code、claude-code、想在 ArkClaw 里用 Anthropic 官方 Coding CLI、提到 ark-code-latest / 火山方舟 AgentPlan 接 claude code、想切换 claude code 的模型供应商、需要做代码 review / 代码改写、或者说"我没有 Anthropic 官方 API Key 但想用 claude code"时,使用本 skill。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 13
✓ No critical or high findings
Medium and low: 13
-
medium Dangerous commands
cmd-shell-rcscripts/helpers.sh:125Writes to a shell startup filesed -i "/^export $var_name=/d" "$HOME/.bashrc" 2>/dev/null || true
-
medium Dangerous commands
cmd-shell-rcscripts/helpers.sh:126Writes to a shell startup fileecho "export $var_name=\"$var_val\"" >> "$HOME/.bashrc"
-
medium Dangerous commands
cmd-shell-rcscripts/install.sh:30Writes to a shell startup fileecho 'export PATH="$HOME/.npm-global/bin:$PATH"' >> "$HOME/.bashrc"
-
low Dangerous commands
cmd-background-processreferences/routing-flow.md:96Starts a background / autostarted processnohup setsid claude -p "..." </dev/null > "$LOG_FILE" 2>&1 &
-
low Dangerous commands
cmd-background-processreferences/routing-flow.md:111Starts a background / autostarted process (documentation table row)| `nohup setsid` | 完全脱离 controlling tty,不受父进程的信号影响 | 否则父 shell 退出会带走 claude |
table -
low Dangerous commands
cmd-background-processreferences/troubleshooting.md:79Starts a background / autostarted process (quoted — discussed, not commanded)- run.sh 内部已经做好了 `nohup setsid + </dev/null + log file + 110s 超时` 三件套
quoted -
low Dangerous commands
cmd-background-processreferences/troubleshooting.md:87Starts a background / autostarted processnohup setsid claude -p "改个东西" --allowedTools "Read,Edit,Write,Bash" </dev/null > /tmp/claude.log 2>&1 &
-
low Dangerous commands
cmd-background-processscripts/run.sh:18Starts a background / autostarted process (code comment)# nohup setsid claude ... </dev/null > log 2>&1 &
comment -
low Dangerous commands
cmd-background-processscripts/run.sh:136Starts a background / autostarted process (code comment)# --- 启动: nohup setsid + </dev/null + log file ---
comment -
low Dangerous commands
cmd-background-processscripts/run.sh:137Starts a background / autostarted process (code comment)# setsid 把 claude 放进新会话,完全脱离任何可能的 controlling tty
comment -
low Dangerous commands
cmd-background-processscripts/run.sh:140Starts a background / autostarted processnohup setsid claude "${CLAUDE_ARGS[@]}" </dev/null >"$LOG_FILE" 2>&1 & -
low Dangerous commands
cmd-background-processSKILL.md:226Starts a background / autostarted process (detector / deny-list definition)2. 用 `nohup setsid + </dev/null + log file + 110s PID polling` 跑 claude(避免 PTY 挂起)
detector -
low Dangerous commands
cmd-background-processSKILL.md:261Starts a background / autostarted process (documentation table row)| 110s 超时是硬约束 | 走 `nohup setsid + log file + while-poll PID` 路径;一旦 PID 还活着且超过 110s,主动 `kill -9`,从日志里取已生成的内容 |
table
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2723 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 10 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 293: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.