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 asaotomo/DeepSentry --skill webshell-huntgit clone --depth 1 https://github.com/asaotomo/DeepSentryWrote 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/asaotomo/deepsentry/webshell-hunt)<a href="https://agentmods.dev/skills/asaotomo/deepsentry/webshell-hunt"><img src="https://agentmods.dev/badge/skills/asaotomo/deepsentry/webshell-hunt/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/asaotomo/deepsentry/webshell-hunt"><img src="https://agentmods.dev/badge/skills/asaotomo/deepsentry/webshell-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to critical
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 →
- critical YARA Match · line 38 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
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 | $0.00040 | $0.00573 |
| Opus 5.5 | $0.00016 | $0.00229 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
webshell-hunt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Webshell 狩猎 Skill
何时使用
- 用户要求在 Web 目录中查找后门/木马
- 应急响应中需要快速定位 Webshell
- CMS/框架目录出现异常文件
工作流程
阶段 1: 签名扫描（快速但误报多）
find /var/www -name "*.php" -exec grep -l "eval\s*(" {} \; 2>/dev/null
find /var/www -name "*.php" -exec grep -l "base64_decode" {} \; 2>/dev/null
find /var/www -name "*.jsp" -exec grep -l "Runtime.getRuntime" {} \; 2>/dev/null
阶段 2: 行为分析（降低误报）
# 最近 30 天修改的 PHP 文件
find /var/www -name "*.php" -mtime -30 -ls 2>/dev/null
# 非框架目录的可疑文件
find /var/www -name "*.php" -not -path "*/vendor/*" -not -path "*/node_modules/*" -mtime -7
阶段 3: 内容确认
对可疑文件使用 read_file 或 cat 查看内容，识别：
<?php @eval($_POST[...]); ?>— 一句话木马base64_decode+eval组合 — 混淆后门system()/exec()/shell_exec()— 命令执行
阶段 4: 处置建议
- 确认后建议隔离（移动到 quarantine 目录）而非直接删除
- 记录文件 hash:
md5sum <file> - 检查同目录其他文件和访问日志
输出格式
## Webshell 狩猎报告
- 扫描范围: [目录路径]
- 可疑文件: [路径 | 修改时间 | 风险特征]
- 确认木马: [路径 | 类型 | 内容摘要]
- 建议措施: [隔离/删除/监控]
注意事项
- jQuery/CMS 核心文件常有 eval，需结合路径判断
- 优先行为分析（mtime）而非纯签名
- 高危删除操作需用户确认
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.
- 1mo ago First seen · 63 lines · 40 tokens per session scan A 14e4b5c866e6
webshell-hunt is a skill published in the GitHub repository asaotomo/DeepSentry (38 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 573 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
go-expert
Expert-level Go development with Go 1.22+ features, concurrency, standard library, and production-grade best practices. Use when the user mentions concurrency, microservices, or backend, or when the task involves idiomatic Go, goroutines and channels, context-based cancellation, or writing an HTTP server.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
golang-patterns
Go-specific design patterns and best practices including functional options, small interfaces, dependency injection, concurrency patterns, error handling, and package organization. Use when working with Go code to apply idiomatic Go patterns.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
ax-go-gen
Use when writing Go code with github.com/ax-llm/ax/packages/go for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.