AC qinglong
Manage QingLong (青龙) panel via REST API — cron jobs, environment variables, scripts, dependencies, subscriptions, logs and system operations. Use this skill whenever the user mentions QingLong, 青龙面板, scheduled tasks on a self-hosted panel, or wants to manage cron jobs / env vars / scripts on their QingLong instance, even if they don't say "QingLong" explicitly. Also trigger for requests like "帮我查看定时任务", "添加环境变量", "运行脚本", "禁用任务", "查看日志" when the context is a QingLong panel.
As a process C 57/100 · 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 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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-usescripts/ql.sh:60Credential used in a network call (verify the destination is the intended service)response=$(curl -sf "${QL_URL}/open/auth/token?client_id=${QL_CLIENT_ID}&client_secret=${QL_CLIENT_SECRET}" 2>&1) || \
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (qinglong) differs from the folder (qinglong-skills)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 4 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 1252 tokens
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 477: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.