Security audit
Security checks for vulnerabilities and agentic risk
This skill checks product images locally and optionally saves repaired copies; its separate cloud-generation helpers disclose their uploads and credential use.
Use the local checker without API credentials. Review repaired copies for cropping or color changes, and use a separate output directory. If using the generation helpers, explicitly choose a provider and expect image uploads and possible charges. Passing these checks does not guarantee marketplace approval.
Without declared permissions the skill's intent is opaque and cannot be validated.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
这个技能只回答后者：这张图传上去会不会被驳回，卡在哪一条，怎么改。
和 [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 的分工：
detect-task 用视觉模型判断「像不像真的」，主观、要花算力；
本技能读像素做客观判定，不花算力、毫秒级、结论可复现。**两个都过才叫能投。**
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| 不能做 | 去哪 |
| --- | --- |
| 判断有没有文字 / 水印 / 拼图 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 的视觉模型 |
| 判断商品有没有崩 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) |
| 去水印 | [remove-watermark](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/remove-watermark/skill.md) |
| 修图、去褶皱 | [item-repair](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/item-repair/skill.md) |
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| 不能做 | 去哪 |
| --- | --- |
| 判断有没有文字 / 水印 / 拼图 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 的视觉模型 |
| 判断商品有没有崩 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) |
| 去水印 | [remove-watermark](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/remove-watermark/skill.md) |
| 修图、去褶皱 | [item-repair](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/item-repair/skill.md) |
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
拿本仓库 flat-lay 的实际产出图，按 Amazon 主图规则检：
python3 scripts/check_listing.py docs/flat-lay/example-output.jpg --platform amazon
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| 客观规格判定 | 背景纯度、主体占比、分辨率、比例、透明通道、描边、格式、体积、色彩模式 |
| 多平台规则 | Amazon / TikTok Shop / Temu / Shopee / Shopify / 淘宝，可自定义 |
| 自动修复 | 压白底、按目标占比重构画布、补分辨率、压到体积上限 |
| 批量 | 一次传多张，或配合 [batch-image](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/batch-image/skill.md) 整批过 |
| 退出码 | 0 = 可投；1 = 有驳回风险，便于接进 CI 或流水线 |
| 不能做 | 去哪 |
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| --- | --- |
| 判断有没有文字 / 水印 / 拼图 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 的视觉模型 |
| 判断商品有没有崩 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) |
| 去水印 | [remove-watermark](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/remove-watermark/skill.md) |
| 修图、去褶皱 | [item-repair](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/item-repair/skill.md) |
**自动修复的边界**：`--fix` 只做几何与色彩层面的合规化，它不会替你修图。
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| 判断有没有文字 / 水印 / 拼图 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 的视觉模型 |
| 判断商品有没有崩 | [detect-task](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) |
| 去水印 | [remove-watermark](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/remove-watermark/skill.md) |
| 修图、去褶皱 | [item-repair](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/item-repair/skill.md) |
**自动修复的边界**：`--fix` 只做几何与色彩层面的合规化，它不会替你修图。
如果原图本身是糊的、崩的、带水印的，修完还是糊的崩的带水印的。
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
| 无文字水印 | `No text, no logo, no watermark, no inset images, no borders anywhere in the frame.` |
| 方图 | `Square 1:1 composition, product centered.` |
[run_loop](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/detect-task/skill.md) 会自动做这件事：合规校验失败时，
它把上面对应的句子追加进 prompt 再跑一轮，不用人管。
---
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
model: () => env.GEN_MODEL_OPENAI || 'gpt-image-1',
describe(req) {
const ep = req.images?.length ? 'images/edits' : 'images/generations'
return `POST https://api.openai.com/v1/${ep} model=${openai.model()} size=${mapSize(req.size)} n=${req.batch}`
},
async run(req) {
const key = env.OPENAI_API_KEY
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
: await readFile(p)
fd.append('image[]', new Blob([buf], { type: mimeOf(p) }), path.basename(p))
}
r = await fetch('https://api.openai.com/v1/images/edits', {
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
})
} else {
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
: await readFile(p)
fd.append('image[]', new Blob([buf], { type: mimeOf(p) }), path.basename(p))
}
r = await fetch('https://api.openai.com/v1/images/edits', {
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
})
} else {
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
})
} else {
r = await fetch('https://api.openai.com/v1/images/generations', {
method: 'POST',
headers: { authorization: `Bearer ${key}`, 'content-type': 'application/json' },
body: JSON.stringify({
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
})
} else {
r = await fetch('https://api.openai.com/v1/images/generations', {
method: 'POST',
headers: { authorization: `Bearer ${key}`, 'content-type': 'application/json' },
body: JSON.stringify({
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
model: (req) =>
env.GEN_MODEL_REPLICATE ||
(req?.images?.length ? 'black-forest-labs/flux-kontext-pro' : 'black-forest-labs/flux-dev'),
describe(req) { return `POST https://api.replicate.com/v1/models/${replicate.model(req)}/predictions` },
async run(req) {
const input = { prompt: req.prompt, num_outputs: req.batch }
if (req.images?.length) input.input_image = await asDataUri(req.images[0])
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
const input = { prompt: req.prompt, num_outputs: req.batch }
if (req.images?.length) input.input_image = await asDataUri(req.images[0])
const j = await postJson(
`https://api.replicate.com/v1/models/${replicate.model(req)}/predictions`,
{ input },
{ authorization: `Bearer ${env.REPLICATE_API_TOKEN}`, prefer: 'wait' },
req.timeoutMs,
Detected: suspicious.dangerous_exec, suspicious.env_credential_access