DC v19-trust-engine
V19信任计算引擎 — V19能力矩阵首个能力型Skill。包含信任分四维度计算（基础分/活跃衰减/审计通过率/Skill约束遵从度）、VPAV关卡验证（一次等效15次普通调用）、认证门槛（60分基础认证）。公开密钥体验 + 自助注册入口。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 5
-
high Exfiltration
exfil-webhook-urlSKILL.md:72Webhook / callback URL commonly used for exfiltration (verify the destination)curl -s https://boat-atlas-spa-flexible.trycloudflare.com/governance/health \
-
high Exfiltration
exfil-webhook-urlSKILL.md:76Webhook / callback URL commonly used for exfiltration (verify the destination)curl -s https://boat-atlas-spa-flexible.trycloudflare.com/governance/trust-score \
-
high Exfiltration
exfil-webhook-urlSKILL.md:83Webhook / callback URL commonly used for exfiltration (verify the destination)curl -s -X POST https://boat-atlas-spa-flexible.trycloudflare.com/governance/register \
Medium and low: 2
-
medium Exfiltration
exfil-webhook-urlSKILL.md:93Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)- 🔗 治理看板: `https://boat-atlas-spa-flexible.trycloudflare.com/governance/dashboard`
quoted -
low Exfiltration
exfil-webhook-urlskill-card.md:30Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)- [V19 Governance Dashboard](https://boat-atlas-spa-flexible.trycloudflare.com/governance/dashboard) <br>
placeholder
Files scanned: 2. 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
- 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
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 561 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 120: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.