DC panda-imagine
多 Provider 图片生成引擎。支持 OpenAI、Azure、Google Gemini、OpenRouter、 通义万相(DashScope)、MiniMax、即梦(Jimeng)、豆包(Seedream)、Replicate。 支持文生图、参考图、宽高比、批量生成。 触发词："生成图片"、"画图"、"generate image"、"create image"。
As a process C 58/100 · 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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
- 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 · 14
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:156Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://jimeng.jianying.com/cli | bash
Medium and low: 13
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/azure.ts:45Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/dashscope.ts:88Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/google.ts:37Helper 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
-
medium Exfiltration
net-credential-usescripts/providers/google.ts:75Credential used in a network call (verify the destination is the intended service)const res = await fetch(`${base}/models/${model}:generateContent?key=${apiKey}`, { -
medium Exfiltration
net-credential-usescripts/providers/google.ts:104Credential used in a network call (verify the destination is the intended service)const res = await fetch(`${base}/models/${model}:predict?key=${apiKey}`, { -
medium Exfiltration
net-redirectable-api-keyscripts/providers/jimeng.ts:209Helper 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
-
medium Dangerous commands
cmd-pipe-to-shellscripts/providers/jimeng.ts:318Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)" 1. 安装 dreamina CLI（推荐）：curl -fsSL https://jimeng.jianying.com/cli | bash\n" +
code literal -
medium Exfiltration
net-redirectable-api-keyscripts/providers/minimax.ts:42Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/openai.ts:45Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/openrouter.ts:28Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/replicate.ts:37Helper 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
-
medium Exfiltration
net-redirectable-api-keyscripts/providers/seedream.ts:51Helper 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 Dangerous commands
cmd-pipe-to-shellscripts/providers/jimeng.ts:257Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)throw new Error("即梦 API 模式不支持 --ref 参考图。请安装 dreamina CLI（curl -fsSL https://jimeng.jianying.com/cli | bash）以获得参考图支持");detectorcode literal
Files scanned: 16. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1115 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (6 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 187: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.