FC entropy-box-zh
以箱熵（Entropy Box）的方案咨询 Consult 为核心，把边界明确的具身智能技术需求转化为候选实现方法和有依据的工程工作流。先由当前大模型澄清并拆分宽泛需求，分别咨询具体子问题，再用 Search 深入了解已选技术、用 Lookup 锚定实体、用 Evidence 核验依据；同时支持全景定位、能力依赖分析和资产选型。不用于直接控制物理机器人。
以箱熵（Entropy Box）的方案咨询 Consult 为核心，把边界明确的具身智能技术需求转化为候选实现方法和有依据的工程工作流。先由当前大模型澄清并拆分宽泛需求，分别咨询具体子问题，再用 Search 深入了解已选技术、用 Lookup 锚定实体、用 Evidence…
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 · 11
-
high Exfiltration
exfil-webhook-urlREADME.md:60Webhook / callback URL commonly used for exfiltration (verify the destination)- 项目网站：https://xiangshang.ngrok.app/
-
high Exfiltration
exfil-webhook-urlREADME.md:63Webhook / callback URL commonly used for exfiltration (verify the destination)- 在线 API Schema：https://xiangshang.ngrok.app/openapi.json
-
high Exfiltration
exfil-webhook-urlskill-card.md:40Webhook / callback URL commonly used for exfiltration (verify the destination)- [Online API schema](https://xiangshang.ngrok.app/openapi.json)
-
high Exfiltration
exfil-webhook-urlskill-card.md:41Webhook / callback URL commonly used for exfiltration (verify the destination)- [Project website](https://xiangshang.ngrok.app/)
-
high Exfiltration
exfil-webhook-urlSKILL.md:286Webhook / callback URL commonly used for exfiltration (verify the destination)- 项目网站：https://xiangshang.ngrok.app/
-
high Exfiltration
exfil-webhook-urlSKILL.md:290Webhook / callback URL commonly used for exfiltration (verify the destination)- 在线 API Schema：https://xiangshang.ngrok.app/openapi.json
Medium and low: 5
-
medium Exfiltration
exfil-webhook-urlreferences/api.md:3Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)基础地址：`https://xiangshang.ngrok.app`
quoted -
medium Exfiltration
exfil-webhook-urlreferences/api.md:15Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)-X POST "https://xiangshang.ngrok.app/api/search" \
quoted -
medium Exfiltration
exfil-webhook-urlreferences/api.md:55Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)-X POST "https://xiangshang.ngrok.app/api/evidence/search" \
quoted -
medium Exfiltration
exfil-webhook-urlreferences/api.md:83Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)-X POST "https://xiangshang.ngrok.app/api/lookup" \
quoted -
medium Exfiltration
exfil-webhook-urlreferences/api.md:116Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)-X POST "https://xiangshang.ngrok.app/api/consult" \
quoted
Files scanned: 7. 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. 83 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1758 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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
- +2Single-language instructions
- +3Description length 178: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 83 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.