CF china-mirror-resolver
Self-healing China mirror source resolver. Automatically discovers, validates, and configures domestic mirror sources for pip/npm/yarn/pnpm/conda/Docker/Go/ Rust/Maven/Gradle/Homebrew/apt/yum/GitHub/HuggingFace when downloads are slow or timing out in mainland China. Trigger keywords: "换源", "镜像源", "下载慢", "超时", "timeout", "mirror", "registry", "proxy", "connection refused", "SSL error", "443", "ETIMEDOUT", "CondaHTTPError", "pip install failed".
As a process F 50/100 · Will not run — References files that are not bundled: scripts/validate.ps1
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:67Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/vali…ps1
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:68Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/vali…ps1 -Tool docker
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:69Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/vali…ps1 -Json
-
medium Dangerous commands
cmd-privilegereferences/config-templates.md:76Privilege escalation / world-writable permissionssudo cp "$DAEMON_JSON" "${DAEMON_JSON}.bak" -
medium Dangerous commands
cmd-privilegereferences/config-templates.md:78Privilege escalation / world-writable permissionssudo mv "${DAEMON_JSON}.tmp" "$DAEMON_JSON" -
medium Dangerous commands
cmd-privilegereferences/config-templates.md:80Privilege escalation / world-writable permissionsecho "{\"registry-mirrors\": $MIRRORS}" | sudo tee "$DAEMON_JSON" > /dev/null -
medium Dangerous commands
cmd-privilegereferences/config-templates.md:214Privilege escalation / world-writable permissionssudo cp -r /etc/yum.repos.d /etc/yum.repos.d.bak
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: terminalallowed-tools: WebSearch WebFetch terminal file-read file-write
-
low Dangerous commands
cmd-privilegereferences/config-templates.md:77Privilege escalation / world-writable permissions (detector / deny-list definition)jq --argjson mirrors "$MIRRORS" '. + {"registry-mirrors": $mirrors}' "$DAEMON_JSON" | sudo tee "${DAEMON_JSON}.tmp" > /dev/nulldetector
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/validate.ps1 - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 50/100
- 0Tools and files. 1 referenced file(s) missing: scripts/validate.ps1
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4248 tokens
- 100Steps. 20 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (50 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 448: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.