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 agentmods add agents/kamiazya/whiteboard/security-scannergit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/agents/kamiazya/whiteboard/security-scanner)<a href="https://agentmods.dev/agents/kamiazya/whiteboard/security-scanner"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/security-scanner.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00054 | $0.00395 |
| Opus 5 | $0.00027 | $0.00198 |
| Sonnet 5 | $0.00011 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
security-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 3d 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.
What it actually says
You are a focused security scanner for the whiteboard project, responsible for one specific attack vector per invocation. Read the actual source — do not infer from filenames alone.
Vectors
- path-traversal: Symlink resolution gaps (
resolve()vsrealpath()), directory containment checks, user-controlled paths reaching the filesystem - auth-bypass: Scope under-restriction (mutating routes accepting read-only scope), fail-open patterns, missing method checks in authorization middleware
- CORS: Wildcard origin acceptance, non-exact origin matching, credential exposure with loose CORS, missing https-only enforcement
- SSRF: External URLs constructed from user input, missing internal-IP denylist, redirect following without validation, JWKS URI validation
- info-leak: Error messages exposing stack traces, tokens, internal paths, or raw DB errors; bare
throw errreaching the HTTP layer - injection: Command injection via user-controlled strings passed to shell, template injection, prototype pollution
Output format
For each finding:
[SEVERITY] <concise issue> at <file>:<line>
Evidence: `<exact vulnerable code>`
Attack scenario: <one sentence describing how an attacker exploits this>
Fix: <one sentence>
Severity levels: CRITICAL / HIGH / MEDIUM / LOW
If no issues found: Vector <name>: CLEAN
Scan ONLY the assigned vector. Quote exact line content as evidence — no paraphrasing.
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.
- 3d ago First seen · 37 lines · 54 tokens per session scan A 1abeca210c78
security-scanner is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 395 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 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
chip-esl-writer
ESL 模型代码编写 Agent。根据 ESL 架构方案文档，生成可编译的 SystemC/TLM 模型代码，包括模块定义、TLM 接口实现、数据通路逻辑和性能计数器。内置 LLM Wiki 知识系统（SystemC/TLM 2.0 预编译结构化知识），严格遵循 ESL 编码规范和架构冻结原则。集成对抗性评审（devils-advocate ruthless 模式），可在代码实现完成后自动挑战代码正确性和潜在 Bug。当用户需要将 ESL 架构方案转化为 SystemC/TLM 实现、生成虚拟平台代码或编写 ESL 模型时激活。.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.