Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZJU-REAL/Easel --skill skill-risk-scannergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/skill-risk-scanner)<a href="https://agentmods.dev/skills/zju-real/easel/skill-risk-scanner"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-risk-scanner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/skill-risk-scanner"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-risk-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00151 | $0.02213 |
| Opus 5 | $0.00076 | $0.01107 |
| Sonnet 5 | $0.00030 | $0.00443 |
| Haiku 4.5 | $0.00015 | $0.00221 |
Grade A, and why
skill-risk-scanner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容原创度与版权风险评估
基于 LLM 文本分析能力，评估内容的原创度风险和素材版权风险，输出定性风险报告与改进建议。
能力边界声明
本 SKILL 基于 LLM 文本分析，不包含以下技术能力：
- 不做技术查重 — 无法计算余弦相似度或精确重复率，需要 Copyleaks / Originality.ai 等外部 API
- 不输出相似度分数 — 所有风险判断均为定性等级（低/中/高），不伪造百分比或小数
- 不做图片内容识别 — 无法读取 EXIF、检测水印、识别图片来源；图片风险评估基于用户提供的来源描述
- 不做音频指纹匹配 — 无法识别 BGM 曲目，基于用户标注的音乐来源进行风险判断
与其他 SKILL 的区别
| SKILL | 定位 | 检查焦点 |
|---|---|---|
| risk-scanner（本 SKILL） | 原创度 + 版权风险 | 洗稿模式识别、素材版权风险、引用合规 |
| skill-quality-gate | 平台合规 + 内容质量 | 敏感词、平台规则、广告法、绝对化用语、医疗违规 |
| skill-publish-checklist | 完整性检查 | 有没有漏标题、漏封面 |
输入
| 参数 | 必填 | 说明 |
|---|---|---|
| 待检查文案 | 是 | 文案正文、脚本、长文原稿 |
| 素材来源说明 | 否 | 用户描述图片/音频/视频的来源（如"图片来自 Unsplash"、"BGM 用的抖音自带音乐"） |
| 参考来源文本 | 否 | 原始参考文章的文本或 URL，用于对比改写充分度 |
| 目标平台 | 否 | 发布平台名称，用于匹配平台版权规则 |
输出
Markdown 格式的风险评估报告，结构如下：
# 风险评估报告
## 整体风险等级：🟢 低风险 / 🟡 中风险 / 🔴 高风险
## 一、文本原创度评估
### 洗稿模式扫描
- [扫描结果与具体发现]
### 内容独特性判断
- [是否包含个人经验/独家数据/原创观点]
### 引用规范检查
- [引用是否标注来源、数据是否注明出处]
## 二、素材版权风险（仅在用户提供素材来源描述时输出）
### 图片素材
- [基于用户描述的来源判断]
### 音频/BGM
- [基于用户描述的来源判断]
## 三、品牌与商标风险
- [文案中提及的品牌名/商标的使用风险]
## 四、风险清单
### 必须处理（阻塞发布）
- [高风险项]
### 建议处理（不阻塞但有隐患）
- [中风险项]
## 五、改进建议
- [针对每个风险项的具体操作建议]
风险等级定义：
- 低风险 — 内容有明显原创成分，引用规范，素材来源清晰
- 中风险 — 存在部分洗稿嫌疑或素材来源不明，建议修改后发布
- 高风险 — 有明显搬运/抄袭模式或版权侵权风险，不建议直接发布
执行步骤
Step 1 — 确认输入与检查范围
- 读取用户提供的待检查文案
- 确认是否提供了素材来源说明（图片、音频、视频的来源描述）
- 确认是否提供了参考来源文本（用于对比改写充分度）
- 确认目标平台（用于匹配平台特有版权规则）
- 未提供素材来源说明时，跳过素材版权评估模块，在报告中注明"用户未提供素材来源信息，无法评估素材版权风险"
Step 2 — 文本洗稿模式扫描
逐段扫描文案，按 references/washing-patterns.md「一、洗稿模式识别」识别机械性同义替换、句式变换但论点复刻、段落搬运重排三类特征。对发现的每个特征引用具体段落文本并说明理由；未发现时明确说明"未检测到明显洗稿模式"。
Step 3 — 内容独特性评估
按 references/washing-patterns.md「二、内容独特性评估」判断文案是否包含个人经验、独家数据、原创观点、具体细节，并据此给出原创度较高/一般/低的结论。
Step 4 — 引用规范检查
按 references/washing-patterns.md「三、引用规范检查」核对观点引用、数据引用、截图引用的来源标注；若用户提供了参考来源文本，对比本文与来源的转述充分度（是否只换词不换意、是否加入自己的分析、是否改变结构和论证逻辑）。
Step 5 — 素材版权风险评估（基于用户描述）
仅在用户提供素材来源描述时执行此步骤。
根据用户描述的素材来源，参照 references/copyright-guide.md「七、素材来源风险速查表」（图片 7.1 / 音频 BGM 7.2）判断风险等级，并对高风险素材推荐 references/copyright-guide.md 中的免费图库和音乐库替代来源。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 165 lines · 151 tokens per session scan A e30054b433f0
skill-risk-scanner is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 151 tokens to every session and 2,213 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
dragoncraft-reason
A Chinese-language coach for turning case facts, disputed points, legal rules, and a position into a structured legal narrative. It can produce opening statements, closing arguments, and evidence-to-story mappings.
osint-investigation
Public-records OSINT: SEC, sanctions, courts, property.
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
meta-compliance-audit-bundle
Auditable compliance bundle: deep-research with citations → signable .docx report → read-only PDF archive → memory note of audit findings.
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
brand-name-checker
Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Returns a risk level and Proceed/Modify/Abandon recommendation. Skip for name brainstorming, logo design, or trademark filings.