bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 bytedance/agentkit-samples --skill byted-security-llmscannergit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/byted-security-llmscanner)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-security-llmscanner"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-security-llmscanner.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 18 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 20 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 86 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 98 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 107 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 119 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 133 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 136 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 149 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 159 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 172 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 183 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 199 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 202 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 205 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 236 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 254 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 289 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.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 309 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.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00059 | $0.02920 |
| Opus 5 | $0.00030 | $0.01460 |
| Sonnet 5 | $0.00012 | $0.00584 |
| Haiku 4.5 | $0.00006 | $0.00292 |
Grade A, and why
byted-security-llmscanner 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 4d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大模型安全测评全流程管理技能使用指南
触发条件
当用户发送包含"创建资产"、"更新资产"、"发起测评"、"分析测评"、"查询资源"等关键词的指令时，触发本技能。
脚本位置说明
脚本目录： ~/.openclaw/workspace/skills/byted-security-llmscanner/scripts/
执行方式：
cd ~/.openclaw/workspace/skills/byted-security-llmscanner/scripts
npx ts-node src/create_asset_model.ts <参数...>
以下示例均需先进入脚本目录
⚠️ 易错点说明
1. 资产ID vs 资产名称
update_asset_model.ts的第一个参数是Name（资产名称），不是AssetID。脚本会自动根据名称和ModelID查询资产ID。update_asset_agent.ts的参数是<AgentID> <Name> <PlatformID>，需要同时提供资产ID和名称。
2. 脚本代码问题
- 部分脚本可能存在重复属性问题（如
proxy: false重复），导致 TypeScript 编译错误。如遇此类错误，需要检查并修复脚本代码。
3. 模态类型匹配
- 资产的模态类型必须包含测评集的模态类型，否则无法发起测评。
- 例如：测评集是
text2text，资产的模态类型可以是text2text或text2text,image2text，但不能只有image2text。
4. 智能体平台参数
- 不同智能体平台需要不同的参数，必须先用
list_agent_platforms.ts vars <PlatformID>查询该平台需要的参数。
5. 安全测评剧本适用范围
- 部分安全测评剧本专门针对 OpenClaw，部分是通用的。查询剧本时会显示
assetTypes[] 字段，如果为空则表示通用。
通用枚举
模态类型
text2text：文生文image2text：图文生文text2image：文生图
资产类型
model：大模型agent：智能体openclaw：OpenClaw 资产
合规测评任务状态
| 状态码 | 状态名称 | 说明 |
|---|---|---|
| 0 | 待测评 | 任务已创建，等待开始执行 |
| 1 | 测评中 | 任务正在执行 |
| 2 | 测评成功 | 任务执行完成（终态） |
| 3 | 测评异常 | 任务执行失败（终态） |
| 5 | 暂停测评 | 任务被暂停（终态） |
| 6 | 终止测评 | 任务被终止（终态） |
安全测评任务状态
| 状态码 | 状态名称 | 说明 |
|---|---|---|
| 10 | 等待处理 | 任务已创建，等待开始执行 |
| 20 | 处理中 | 任务正在执行 |
| 30 | 异常 | 任务执行失败（终态） |
| 40 | 完成 | 任务执行完成（终态） |
资产管理
1. 创建大模型资产
调用：
npx ts-node src/create_asset_model.ts <Name> <ModelID> <BaseUrl> <ApiKey> [ModalTypes]
参数：
Name：资产名称（如：deepseek-v3）ModelID：模型 ID（如：ep-20250325142301-ljxvm）BaseUrl：API 地址（如：https://ark-cn-beijing.bytedance.net/api/v3）ApiKey：API 密钥（如：sk-xxxxxxxxxxxx）ModalTypes：模态类型（可选，逗号分隔，默认：text2text）
示例：
npx ts-node src/create_asset_model.ts deepseek-v3 ep-20250325142301-ljxvm https://ark-cn-beijing.bytedance.net/api/v3 sk-xxxxxxxxxxxx text2text
2. 更新大模型资产
What ships with it
21 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.
- LICENSE 9.9 KB
- README.md 16 KB
- scripts/config.ts 793 B runs code
- scripts/data/.gitkeep 0 B
- scripts/package-lock.json 18 KB
- scripts/package.json 375 B
- scripts/src/analyze_rt_task.ts 11 KB runs code
- scripts/src/analyze_task_data.ts 7.2 KB runs code
- scripts/src/common.ts 5.0 KB runs code
- scripts/src/create_asset_agent.ts 5.4 KB runs code
- scripts/src/create_asset_model.ts 6.7 KB runs code
- scripts/src/create_rt_task.ts 4.3 KB runs code
- scripts/src/create_task.ts 3.7 KB runs code
- scripts/src/fetch_lists.ts 17 KB runs code
- scripts/src/list_agent_platforms.ts 4.0 KB runs code
- scripts/src/list_resources.ts 22 KB runs code
- scripts/src/list_rt_scenarios.ts 2.4 KB runs code
- scripts/src/run_analysis.ts 7.0 KB runs code
- scripts/src/update_asset_agent.ts 5.3 KB runs code
- scripts/src/update_asset_model.ts 7.4 KB runs code
- scripts/tsconfig.json 401 B
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.
- 4d ago First seen · 347 lines · 59 tokens per session scan A e5e7dbe739a3
byted-security-llmscanner is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,920 once invoked, about $0.0003 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
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.