DC bootstrap-china-network
Main entry point for configuring and diagnosing all development tools in China's network environment. Detects installed tools (pip/uv/poetry, npm/yarn/pnpm, docker, apt, cargo, go, conda, flutter, homebrew), checks for proxy conflicts, and applies appropriate mirror configurations for each. Also provides comprehensive network diagnostics — tests connectivity to official and mirror sources, detects current mirror configuration status, and generates actionable recommendations. This is a self-contained skill — all setup and diagnostic scripts are bundled in the scripts/ subdirectory. Use this skill when the user wants to configure everything at once, is setting up a new development machine in China, or doesn't know which specific tool is slow. Also use when the user says "配置国内镜像", "网络太慢全部配一下", "为什么下载慢", "诊断网络", "diagnose network", or describes a general "slow downloads in China" problem. Use for diagnostics when the user wants to audit their environment, compare mirror speeds, or troubleshoot network issues before applying mirror configurations. For individual tool fixes, still use this skill and run only the relevant script.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Shorten the description to 1024 characters.
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-privilegescripts/apt/setup.sh:140Privilege escalation / world-writable permissionssudo bash -c "source ${SCRIPT_DIR}/../common.sh && backup_file $SOURCES_LIST apt" -
medium Dangerous commands
cmd-privilegescripts/docker/setup.sh:101Privilege escalation / world-writable permissionssudo bash -c "source ${SCRIPT_DIR}/../common.sh && backup_file /etc/apt/sources.list.d/docker.list docker" -
medium Dangerous commands
cmd-privilegescripts/docker/setup.sh:109Privilege escalation / world-writable permissionssudo rm -f /etc/apt/sources.list.d/docker.list
-
medium Exfiltration
net-credential-usescripts/docker/setup.sh:128Credential used in a network call (verify the destination is the intended service)curl -fsSL "${mirror_url}/linux/${distro_id}/gpg" -o "$keyring_dir/docker.asc" -
medium Exfiltration
net-credential-usescripts/docker/setup.sh:132Credential used in a network call (verify the destination is the intended service)curl -fsSL "${mirror_url}/linux/${distro_id}/gpg" | sudo tee "$keyring_dir/docker.asc" > /dev/null -
medium Dangerous commands
cmd-privilegescripts/docker/setup.sh:132Privilege escalation / world-writable permissionscurl -fsSL "${mirror_url}/linux/${distro_id}/gpg" | sudo tee "$keyring_dir/docker.asc" > /dev/null -
medium Dangerous commands
cmd-privilegescripts/docker/setup.sh:133Privilege escalation / world-writable permissionssudo chmod a+r "$keyring_dir/docker.asc"
-
medium Dangerous commands
cmd-privilegescripts/docker/setup.sh:145Privilege escalation / world-writable permissionsecho "$repo_line" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
-
medium Dangerous commands
cmd-pipe-to-shellscripts/rust/setup.sh:118Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)log_info "Then run: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh"
code literal -
low Dangerous commands
cmd-privilegescripts/apt/setup.sh:153Privilege escalation / world-writable permissions (detector / deny-list definition)echo "$new_sources" | sudo tee "$SOURCES_LIST" > /dev/null
detector -
low Exfiltration
net-credential-usescripts/github/setup.sh:177Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)git config --global "${git_config_key}" "https://github.com/"known servicequoted -
low Dangerous commands
cmd-privilegeSKILL.md:96Privilege escalation / world-writable permissions (documentation of a security skill)sudo bash "$SKILL_DIR/scripts/apt/setup.sh" --mirror tuna
security skill
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1141 chars, limit 1024
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (bootstrap-china-network) differs from the folder (china-mirror-skills)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 11 steps
- 100Execution cost. Instruction body is 1026 tokens
- 100Running it twice. Mutating operations check current state
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1140: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 4 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.