BF yufluentcn-ecommerce-imaging
跨境电商 AI 生图：白底图、场景图、实拍抠图、多角度套装、多平台尺寸。 经 Yufluent 云端 Replicate 代理（Qwen-Image 等），按张计费。 配合 visual-craft 工作流 brief→生图→合规。 Use for 生成产品白底图、场景图、AI 电商图片、产品摄影、主图.
跨境电商 AI 生图：白底图、场景图、实拍抠图、多角度套装、多平台尺寸。 经 Yufluent 云端 Replicate 代理（Qwen-Image 等），按张计费。 配合 visual-craft 工作流 brief→生图→合规。 Use for 生成产品白底图、场景图、AI 电商图片、产品摄影、主图.
As a process F 35/100 · Will not run — References files that are not bundled: scripts/image_generator.py, scripts/prompt_library.py
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
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
net-credential-useREADME.md:22Credential used in a network call (verify the destination is the intended service)$env:TOKENAPI_BASE_URL = "http://loca…080/v1"
-
medium Exfiltration
net-redirectable-api-keyscripts/yufluent_api.py:232Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Exfiltration
read-dotenvREADME.md:12Reads a .env filecopy .env.example .env
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/image_generator.py - warning
missing-refreference to a missing file: scripts/prompt_library.py
Process rating: all ten parameters 35/100
- 0Tools and files. 2 referenced file(s) missing: scripts/image_generator.py, scripts/prompt_library.py
- 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
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 877 tokens
- 100Running it twice. No mutating operations
- low 11 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
- -2localhost URLs: will not work for another user
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -33 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 153: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.