BD qinglong
青龙面板管理助手。当用户需要操作青龙面板（定时任务/环境变量/脚本/订阅/依赖/系统设置）时触发。支持自然语言操作，例如："列出所有任务"、"添加环境变量"、"运行任务"、"查看日志"等。
As a process D 49/100 · Unfinished process — 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 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.
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
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Exfiltration
net-credential-useapi-reference.md:255Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $TOKEN" "http://192.168.1.100:5700/api/crons" | python3 -c "
-
medium Exfiltration
net-credential-useapi-reference.md:275Credential used in a network call (verify the destination is the intended service)curl -s -X PUT -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash WebFetch Read Write Edit
-
low Exfiltration
net-credential-useapi-reference.md:267Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable)IDS=$(curl -s -H "Authorization: Bearer $TOKEN" "http://<HOST>/api/crons" | python3 -c "
variable host
Files scanned: 3. 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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (qinglong) differs from the folder (qinglong-skill)
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 1018 tokens
- 100Running it twice. No mutating operations
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 94: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.