ecosystem-security

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Security Ecosystem

安全生态系统

This ecosystem ensures the security of the Agent Platform and all skills within it across three layers: pre-deployment audit, runtime protection, and continuous adaptive defense. Two core skills complement each other — one audits the skills, the other inspects the messages.

该生态系统通过三层机制保障Agent平台及平台内所有Skill的安全：部署前审计、运行时防护和持续自适应防御。两个核心Skill相辅相成——一个负责审计Skill，另一个负责检查消息。

Ecosystem Map

生态系统架构图

text

PRE-DEPLOYMENT         RUNTIME               LEARNING
──────────────         ─────────────         ──────────
security-auditor    →    adaptive-guard   →    Rule engine
  │                      │                    update
  │ Audit                │ K0-K4               │
  │ Trust Score          │ Gradual filter      │ async
  │ Guard rules          │ LLM Judge           │
  ▼                      ▼                    ▼
security-report.md   guard-decision.json   learned-rules.md
trust-score.md       incident-report.md    guard-metrics.md

text

PRE-DEPLOYMENT         RUNTIME               LEARNING
──────────────         ─────────────         ──────────
security-auditor    →    adaptive-guard   →    Rule engine
  │                      │                    update
  │ Audit                │ K0-K4               │
  │ Trust Score          │ Gradual filter      │ async
  │ Guard rules          │ LLM Judge           │
  ▼                      ▼                    ▼
security-report.md   guard-decision.json   learned-rules.md
trust-score.md       incident-report.md    guard-metrics.md

Skill Catalog

Skill目录

🔍 security-auditor

What it does: Statically analyzes a SKILL.md file, detects security vulnerabilities, assigns a trust score, and generates runtime guard rules. Modes: Audit (static analysis) · Trust (authorization mapping) · Guard rule generation Input: A SKILL.md file or the entire ecosystem directory Output: security-report.md · trust-score.md · runtime-violations.md Triggers: When a new skill is written, updated, or prior to production deployment Next skill: adaptive-guard (receives the generated guard rules) Dependency: None — starting point

功能： 对SKILL.md文件进行静态分析，检测安全漏洞，分配信任分数，并生成运行时防护规则。 模式： 审计（静态分析）· 信任（授权映射）· 防护规则生成 输入： 单个SKILL.md文件或整个生态系统目录 输出： security-report.md · trust-score.md · runtime-violations.md 触发条件： 当新Skill编写完成、更新时，或生产部署前 后续Skill： adaptive-guard（接收生成的防护规则） 依赖： 无——为起始节点

🛡️ adaptive-guard

What it does: Passes every incoming message through a 5-tier filter. Gradually deepens from K0 (cache) to K4 (human approval). Synthesizes generalized new rules from every detected attack. Adds less than 50ms latency to the main workflow. Modes: Realtime Guard · Learning Engine · Performance Monitoring Input: Incoming message + user profile + active rule set Output: guard-decision.json · learned-rules.md · guard-metrics.md Triggers: On every incoming message (automatic) · On attack detection Dependency: Guard rules generated by security-auditor (optional, operates with default rules if absent)

功能： 将每条传入消息通过5层过滤器处理。从K0（缓存）到K4（人工审批）逐步深化检测。从每次检测到的攻击中合成通用新规则。对主工作流的延迟增加不超过50毫秒。 模式： 实时防护 · 学习引擎 · 性能监控 输入： 传入消息 + 用户配置文件 + 活跃规则集 输出： guard-decision.json · learned-rules.md · guard-metrics.md 触发条件： 每条消息传入时（自动触发）· 检测到攻击时 依赖： security-auditor生成的防护规则（可选，若无则使用默认规则运行）

Skill Relationship Matrix

Skill关系矩阵

	security-auditor	adaptive-guard
security-auditor	—	Feeds Guard rules
adaptive-guard	Sends rule updates	—

Data Flow:

text

security-auditor audit output
  → trust-score.md (used by adaptive-guard as trust threshold)
  → security-report.md (added to adaptive-guard K1 rules)

adaptive-guard attack detection
  → incident-report.md (appended to security-auditor's next audit)
  → learned-rules.md (feedback loop to K1 static rules)

	security-auditor	adaptive-guard
security-auditor	—	提供防护规则
adaptive-guard	发送规则更新	—

数据流：

text

security-auditor audit output
  → trust-score.md (used by adaptive-guard as trust threshold)
  → security-report.md (added to adaptive-guard K1 rules)

adaptive-guard attack detection
  → incident-report.md (appended to security-auditor's next audit)
  → learned-rules.md (feedback loop to K1 static rules)

Supported Platforms

支持的平台

Platform	security-auditor	adaptive-guard
Claude Code / claude.ai	✅ Full	✅ Full
Telegram Agent	✅ Audit	✅ K0-K3
WhatsApp Agent	✅ Audit	✅ K0-K3
CI/CD Pipeline	✅ Audit	⚠️ K0-K1 (speed-focused)
Local Dev	✅ Full	✅ K0-K2 (ML optional)

平台	security-auditor	adaptive-guard
Claude Code / claude.ai	✅ 完全支持	✅ 完全支持
Telegram Agent	✅ 审计功能	✅ K0-K3
WhatsApp Agent	✅ 审计功能	✅ K0-K3
CI/CD Pipeline	✅ 审计功能	⚠️ K0-K1（侧重速度）
Local Dev	✅ 完全支持	✅ K0-K2（ML可选）

Ecosystem Trigger Conditions

生态系统触发条件

text

/security-ecosystem          → Full ecosystem
@ecosystem-security          → Triggers the orchestrator

Automatic triggers:
  When a new skill is added  → security-auditor (Audit + Trust)
  When a message arrives     → adaptive-guard (always)
  When a skill is updated    → security-auditor (re-audit)
  When an attack is detected → Both (incident + rule update)

text

/security-ecosystem          → Full ecosystem
@ecosystem-security          → Triggers the orchestrator

Automatic triggers:
  When a new skill is added  → security-auditor (Audit + Trust)
  When a message arrives     → adaptive-guard (always)
  When a skill is updated    → security-auditor (re-audit)
  When an attack is detected → Both (incident + rule update)

Ecosystem Metadata

生态系统元数据

yaml

start_point: security-auditor
runtime_skill: adaptive-guard
always_active: [adaptive-guard]
pre_deploy_mandatory: [security-auditor]
can_run_parallel: false      # dependent on each other, sequential
security_level: critical
performance_impact: low      # 50ms target

yaml

start_point: security-auditor
runtime_skill: adaptive-guard
always_active: [adaptive-guard]
pre_deploy_mandatory: [security-auditor]
can_run_parallel: false      # dependent on each other, sequential
security_level: critical
performance_impact: low      # 50ms target

Expansion Roadmap

扩展路线图

Skills to be added:

Skill	Priority	Status
skill-integrity-checker	High	Planned
content-sanitizer	High	Planned
tool-call-auditor	Medium	Planned
behavioral-baseline	Medium	Research
chain-shadow-detector	Low	Research

待添加的Skill：

Skill	优先级	状态
skill-integrity-checker	高	规划中
content-sanitizer	高	规划中
tool-call-auditor	中	规划中
behavioral-baseline	中	研究中
chain-shadow-detector	低	研究中