BF qwencloud-image-generation
[QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qwencloud-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qwencloud-vision), video generation (use qwencloud-video-generation), text-only tasks.
As a process F 69/100 · Will not run — References files that are not bundled: references/codingplan.md, references/custom-oss.md
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keyscripts/qwencloud_lib.py:257Helper 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
net-credential-useSKILL.md:110Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host; quoted — discussed, not commanded)- **API Key**: Check that `DASHSCOPE_API_KEY` (or `QWEN_API_KEY`) is set using a **non-plaintext** check only (e.g. in shell: `[ -n "$DASHSCOPE_API_KEY" ]`; report only "set" or "not set", never the k
demovendor-hostquoted
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5866 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/codingplan.md - warning
missing-refreference to a missing file: references/custom-oss.md
Process rating: all ten parameters 69/100
- 0Tools and files. 2 referenced file(s) missing: references/codingplan.md, references/custom-oss.md
- 30Running it twice. 5 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5866 tokens
- 100Steps. 37 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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)
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 742: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.