The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
docs: resolve markdownlint errors across translated docs
Affaan Mustafadbdbcef58f89
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex d83712888..c0b1dc452 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -73,7 +73,7 @@ git add . && git commit -m "feat: add my-skill" && git push -u origin feat/my-coSkills are knowledge modules that Claude Code loads based on context.-> ** Comprehensive Guide:** For detailed guidance on creating effective skills, see [Skill Development Guide](docs/SKILL-DEVELOPMENT-GUIDE.md). It covers:+> **Comprehensive Guide:** For detailed guidance on creating effective skills, see [Skill Development Guide](docs/SKILL-DEVELOPMENT-GUIDE.md). It covers:> - Skill architecture and categories> - Writing effective content with examples> - Best practices and common patternsdiff --git a/SECURITY.md b/SECURITY.mdindex 18eae85ac..f5d7ee81f 100644--- a/SECURITY.md+++ b/SECURITY.md@@ -14,7 +14,7 @@ If you discover a security vulnerability in ECC, please report it responsibly.**Do not open a public GitHub issue for security vulnerabilities.**-Instead, email **[email protected]** with:+Instead, email **<[email protected]>** with:- A description of the vulnerability- Steps to reproducediff --git a/docs/ja-JP/commands/multi-plan.md b/docs/ja-JP/commands/multi-plan.mdindex dc8406bcf..724a49958 100644--- a/docs/ja-JP/commands/multi-plan.md+++ b/docs/ja-JP/commands/multi-plan.md@@ -207,8 +207,8 @@ Claudeの統合計画での欠落リスクを減らすために、両方のモ**計画が生成され、`.claude/plan/actual-feature-name.md`に保存されました****上記の計画をレビューしてください。以下のことができます:**- - **計画を変更**: 調整が必要なことを教えてください、計画を更新します- - **計画を実行**: 以下のコマンドを新しいセッションにコピー+- **計画を変更**: 調整が必要なことを教えてください、計画を更新します+- **計画を実行**: 以下のコマンドを新しいセッションにコピー```/ccg:execute .claude/plan/actual-feature-name.mddiff --git a/docs/pt-BR/agents/refactor-cleaner.md b/docs/pt-BR/agents/refactor-cleaner.mdindex 3258e554b..8785e85e8 100644--- a/docs/pt-BR/agents/refactor-cleaner.md+++ b/docs/pt-BR/agents/refactor-cleaner.md@@ -82,4 +82,4 @@ Após cada lote:- Todos os testes foram aprovados- Compilação concluída com sucesso- Sem regressões-- Tamanho do pacote reduzido\ No newline at end of file+- Tamanho do pacote reduzidodiff --git a/docs/pt-BR/agents/security-reviewer.md b/docs/pt-BR/agents/security-reviewer.mdindex b2bd8861f..54e456753 100644--- a/docs/pt-BR/agents/security-reviewer.md+++ b/docs/pt-BR/agents/security-reviewer.md@@ -105,4 +105,4 @@ Para obter padrões de vulnerabilidade detalhados, exemplos de código, modelos----**Lembre**: Segurança não é opcional. Uma única vulnerabilidade pode causar prejuízos financeiros reais aos usuários. Seja minucioso, seja cauteloso, seja proativo.\ No newline at end of file+**Lembre**: Segurança não é opcional. Uma única vulnerabilidade pode causar prejuízos financeiros reais aos usuários. Seja minucioso, seja cauteloso, seja proativo.diff --git a/docs/pt-BR/commands/eval.md b/docs/pt-BR/commands/eval.mdindex 7719af189..780f82a00 100644--- a/docs/pt-BR/commands/eval.md+++ b/docs/pt-BR/commands/eval.md@@ -29,6 +29,7 @@ Created: $(date)### Critérios de Sucesso- pass@3 > 90% para evals de capacidade- pass^3 = 100% para evals de regressão+```2. Peça ao usuário para preencher os critérios específicosdiff --git a/docs/tr/README.md b/docs/tr/README.mdindex 98a1de704..9948aabd5 100644--- a/docs/tr/README.md+++ b/docs/tr/README.md@@ -391,8 +391,8 @@ Her component tamamen bağımsızdır.<summary><b>Bu Cursor / OpenCode / Codex / Antigravity ile çalışır mı?</b></summary>Evet. ECC çapraz platformdur:-- **Cursor**: `.cursor/` içinde önceden çevrilmiş config'ler. [Cursor IDE Desteği](#cursor-ide-desteği) bölümüne bakın.-- **OpenCode**: `.opencode/` içinde tam plugin desteği. [OpenCode Desteği](#-opencode-desteği) bölümüne bakın.+- **Cursor**: `.cursor/` içinde önceden çevrilmiş config'ler. [Cursor IDE Desteği](../../README.md#cursor-ide-support) bölümüne bakın.+- **OpenCode**: `.opencode/` içinde tam plugin desteği. [OpenCode Desteği](../../README.md#opencode-support) bölümüne bakın.- **Codex**: macOS app ve CLI için birinci sınıf destek. PR [#257](https://github.com/affaan-m/everything-claude-code/pull/257)'ye bakın.- **Antigravity**: İş akışları, skill'ler ve `.agent/` içinde düzleştirilmiş rule'lar için sıkı entegre kurulum.- **Claude Code**: Native — bu birincil hedeftir.diff --git a/docs/tr/SECURITY.md b/docs/tr/SECURITY.mdindex 2eb41da9c..8cc66a9ec 100644--- a/docs/tr/SECURITY.md+++ b/docs/tr/SECURITY.md@@ -14,7 +14,7 @@ ECC'de bir güvenlik açığı keşfederseniz, lütfen sorumlu bir şekilde bild**Güvenlik açıkları için herkese açık GitHub issue açmayın.**-Bunun yerine, **[email protected]** adresine aşağıdaki bilgilerle e-posta gönderin:+Bunun yerine, **<[email protected]>** adresine aşağıdaki bilgilerle e-posta gönderin:- Güvenlik açığının açıklaması- Yeniden oluşturma adımlarıdiff --git a/docs/tr/TROUBLESHOOTING.md b/docs/tr/TROUBLESHOOTING.mdindex 00f3e5d9c..99f9f38ea 100644--- a/docs/tr/TROUBLESHOOTING.md+++ b/docs/tr/TROUBLESHOOTING.md@@ -6,7 +6,7 @@ Everything Claude Code (ECC) eklentisi için yaygın sorunlar ve çözümler.- [Bellek ve Context Sorunları](#bellek-ve-context-sorunları)- [Ajan Harness Hataları](#ajan-harness-hataları)-- [Hook ve İş Akışı Hataları](#hook-ve-iş-akışı-hataları)+- [Hook ve İş Akışı Hataları](#hook-ve-i̇ş-akışı-hataları)- [Kurulum ve Yapılandırma](#kurulum-ve-yapılandırma)- [Performans Sorunları](#performans-sorunları)- [Yaygın Hata Mesajları](#yaygın-hata-mesajları)diff --git a/docs/tr/commands/learn-eval.md b/docs/tr/commands/learn-eval.mdindex e5220b64d..36d02cc1a 100644--- a/docs/tr/commands/learn-eval.md+++ b/docs/tr/commands/learn-eval.md@@ -75,10 +75,10 @@ origin: auto-extracted**Yönlendirici boyutlar** (karar verirken, puanlanmaz):- - **Spesifiklik ve Uygulanabilirlik**: Hemen kullanılabilir kod örnekleri veya komutlar içerir- - **Kapsam Uyumu**: Ad, tetikleyici koşullar ve içerik hizalanmış ve tek bir desene odaklanmış- - **Benzersizlik**: Mevcut skill'lerin kapsamadığı değer sağlar (kontrol listesi sonuçlarına göre)- - **Yeniden Kullanılabilirlik**: Gelecekteki oturumlarda gerçekçi tetikleyici senaryolar mevcut+- **Spesifiklik ve Uygulanabilirlik**: Hemen kullanılabilir kod örnekleri veya komutlar içerir+- **Kapsam Uyumu**: Ad, tetikleyici koşullar ve içerik hizalanmış ve tek bir desene odaklanmış+- **Benzersizlik**: Mevcut skill'lerin kapsamadığı değer sağlar (kontrol listesi sonuçlarına göre)+- **Yeniden Kullanılabilirlik**: Gelecekteki oturumlarda gerçekçi tetikleyici senaryolar mevcut6. **Karara özel onay akışı**diff --git a/docs/tr/commands/multi-plan.md b/docs/tr/commands/multi-plan.mdindex ea27debb8..8838f2fb6 100644--- a/docs/tr/commands/multi-plan.md+++ b/docs/tr/commands/multi-plan.md@@ -207,8 +207,8 @@ Her iki analizi sentezle, **Adım Adım Implementation Planı** oluştur:**Plan oluşturuldu ve `.claude/plan/actual-feature-name.md` dosyasına kaydedildi****Lütfen yukarıdaki planı inceleyin. Şunları yapabilirsiniz:**- - **Planı değiştir**: Neyin ayarlanması gerektiğini söyleyin, planı güncelleyeceğim- - **Planı çalıştır**: Aşağıdaki komutu yeni bir oturuma kopyalayın+- **Planı değiştir**: Neyin ayarlanması gerektiğini söyleyin, planı güncelleyeceğim+- **Planı çalıştır**: Aşağıdaki komutu yeni bir oturuma kopyalayın```/ccg:execute .claude/plan/actual-feature-name.mddiff --git a/docs/tr/the-security-guide.md b/docs/tr/the-security-guide.mdindex 234f9b33c..516be6a9a 100644--- a/docs/tr/the-security-guide.md+++ b/docs/tr/the-security-guide.md@@ -447,7 +447,7 @@ Kurulumunuzu tarayın: [github.com/affaan-m/agentshield](https://github.com/affaÖnceki kılavuzları okumadıysanız, buradan başlayın:> [Claude Code'un Her Şeyine Dair Kısa Kılavuz](https://x.com/affaanmustafa/status/2012378465664745795)-+>> [Claude Code'un Her Şeyine Dair Uzun Kılavuz](https://x.com/affaanmustafa/status/2014040193557471352)gidip yapın ve ayrıca bu repo'ları kaydedin:diff --git a/docs/zh-CN/CODE_OF_CONDUCT.md b/docs/zh-CN/CODE_OF_CONDUCT.mdindex 77c5ffd04..09caabde4 100644--- a/docs/zh-CN/CODE_OF_CONDUCT.md+++ b/docs/zh-CN/CODE_OF_CONDUCT.md@@ -71,7 +71,7 @@## 归属-本行为准则改编自 \[贡献者公约]\[homepage] 2.0 版本,可访问+本行为准则改编自 [贡献者公约][homepage] 2.0 版本,可访问<https://www.contributor-covenant.org/version/2/0/code_of_conduct.html> 获取。社区影响指南的灵感来源于 [Mozilla 的行为准则执行阶梯](https://github.com/mozilla/diversity)。diff --git a/docs/zh-CN/README.md b/docs/zh-CN/README.mdindex 5cefd63fb..28d7d1b01 100644--- a/docs/zh-CN/README.md+++ b/docs/zh-CN/README.md@@ -874,7 +874,7 @@ cp -r everything-claude-code/rules/common/* ~/.claude/rules/是的。ECC 是跨平台的:* **Cursor**: 预翻译的配置位于 `.cursor/`。参见 [Cursor IDE 支持](#cursor-ide-支持)。-* **OpenCode**: `.opencode/` 中的完整插件支持。参见 [OpenCode 支持](#-opencode-支持)。+* **OpenCode**: `.opencode/` 中的完整插件支持。参见 [OpenCode 支持](#opencode-支持)。* **Codex**: 对 macOS 应用和 CLI 的一流支持,带有适配器漂移防护和 SessionStart 回退。参见 PR [#257](https://github.com/affaan-m/everything-claude-code/pull/257)。* **Antigravity**: 为工作流、技能和扁平化规则紧密集成的设置,位于 `.agent/`。参见 [Antigravity 指南](../ANTIGRAVITY-GUIDE.md)。* **Claude Code**: 原生支持 — 这是主要目标。diff --git a/docs/zh-CN/SECURITY.md b/docs/zh-CN/SECURITY.mdindex 40705859d..0617af048 100644--- a/docs/zh-CN/SECURITY.md+++ b/docs/zh-CN/SECURITY.md@@ -14,7 +14,7 @@**请勿为安全漏洞创建公开的 GitHub 议题。**-请将信息发送至 **[email protected]**,邮件中需包含:+请将信息发送至 **<[email protected]>**,邮件中需包含:* 漏洞描述* 复现步骤diff --git a/docs/zh-CN/commands/learn-eval.md b/docs/zh-CN/commands/learn-eval.mdindex 71fc5802f..1108348a8 100644--- a/docs/zh-CN/commands/learn-eval.md+++ b/docs/zh-CN/commands/learn-eval.md@@ -76,10 +76,10 @@ origin: auto-extracted**指导维度**(用于告知裁决,不进行评分):- * **具体性和可操作性**:包含可立即使用的代码示例或命令- * **范围契合度**:名称、触发条件和内容保持一致,并专注于单一模式- * **独特性**:提供现有技能未涵盖的价值(基于清单结果)- * **可复用性**:在未来的会话中存在现实的触发场景+* **具体性和可操作性**:包含可立即使用的代码示例或命令+* **范围契合度**:名称、触发条件和内容保持一致,并专注于单一模式+* **独特性**:提供现有技能未涵盖的价值(基于清单结果)+* **可复用性**:在未来的会话中存在现实的触发场景6. **裁决特定的确认流程**diff --git a/docs/zh-CN/commands/multi-plan.md b/docs/zh-CN/commands/multi-plan.mdindex 6b8ffa851..5dca189ad 100644--- a/docs/zh-CN/commands/multi-plan.md+++ b/docs/zh-CN/commands/multi-plan.md@@ -215,8 +215,8 @@ mcp__ace-tool__search_context({**请审阅以上计划。您可以:**- * **修改计划**:告诉我需要调整的内容,我会更新计划- * **执行计划**:复制以下命令到新会话+* **修改计划**:告诉我需要调整的内容,我会更新计划+* **执行计划**:复制以下命令到新会话```/ccg:execute .claude/plan/actual-feature-name.mddiff --git a/docs/zh-CN/commands/python-review.md b/docs/zh-CN/commands/python-review.mdindex eb9f7656b..db7f55e50 100644--- a/docs/zh-CN/commands/python-review.md+++ b/docs/zh-CN/commands/python-review.md@@ -314,6 +314,6 @@ result = "".join(str(item) for item in items)| 海象运算符 (`:=`) | 3.8+ || 仅限位置参数 | 3.8+ || Match 语句 | 3.10+ |-| 类型联合 (\`x | None\`) | 3.10+ |+| 类型联合 (`x \| None`) | 3.10+ |确保你的项目 `pyproject.toml` 或 `setup.py` 指定了正确的最低 Python 版本。diff --git a/docs/zh-CN/skills/visa-doc-translate/README.md b/docs/zh-CN/skills/visa-doc-translate/README.mdindex a4515c962..3fc6077d1 100644--- a/docs/zh-CN/skills/visa-doc-translate/README.md+++ b/docs/zh-CN/skills/visa-doc-translate/README.md@@ -4,11 +4,11 @@## 功能-* **自动 OCR**:尝试多种 OCR 方法(macOS Vision、EasyOCR、Tesseract)-* **双语 PDF**:原始图像 + 专业英文翻译-* **多语言支持**:支持中文及其他语言-* **专业格式**:适合官方签证申请-* **完全自动化**:无需人工干预+* **自动 OCR**:尝试多种 OCR 方法(macOS Vision、EasyOCR、Tesseract)+* **双语 PDF**:原始图像 + 专业英文翻译+* **多语言支持**:支持中文及其他语言+* **专业格式**:适合官方签证申请+* **完全自动化**:无需人工干预## 支持的文件类型@@ -80,11 +80,11 @@ pip install pytesseract## 完美适用于-* 澳大利亚签证申请-* 美国签证申请-* 加拿大签证申请-* 英国签证申请-* 欧盟签证申请+* 澳大利亚签证申请+* 美国签证申请+* 加拿大签证申请+* 英国签证申请+* 欧盟签证申请## 许可证diff --git a/docs/zh-CN/the-security-guide.md b/docs/zh-CN/the-security-guide.mdindex 877b67dd0..ab7c227c6 100644--- a/docs/zh-CN/the-security-guide.md+++ b/docs/zh-CN/the-security-guide.md@@ -58,7 +58,7 @@ Moltbook 漏洞暴露了 77 万个智能体的 API 密钥和控制权。五周## 沙盒化-Root 访问权限是危险的。使用单独的服务账户。不要给你的智能体你的个人 Gmail。创建 [email protected]。不要给它你的主 Slack 工作区。创建一个单独的机器人频道。原则很简单。如果智能体被入侵,爆炸半径仅限于一次性账户。使用容器和专用网络来隔离环境。+Root 访问权限是危险的。使用单独的服务账户。不要给你的智能体你的个人 Gmail。创建 <[email protected]>。不要给它你的主 Slack 工作区。创建一个单独的机器人频道。原则很简单。如果智能体被入侵,爆炸半径仅限于一次性账户。使用容器和专用网络来隔离环境。@@ -172,36 +172,35 @@ Unit42 发现,在具有长对话历史的智能体中,持久性提示注入| 来源 | URL || -------------------------------- | --------------------------------------------------------------------------------------------------------------------- |-| Check Point: Claude Code CVEs | https://research.checkpoint.com/2026/rce-and-api-token-exfiltration-through-claude-code-project-files-cve-2025-59536/ |-| OWASP MCP Top 10 | https://owasp.org/www-project-mcp-top-10/ |-| OWASP Agentic Applications Top 10 | https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/ |-| Shannon AI (Keygraph) | https://github.com/KeygraphHQ/shannon |-| Pliny - L1B3RT4S | https://github.com/elder-plinius/L1B3RT4S |-| Pliny - CL4R1T4S | https://github.com/elder-plinius/CL4R1T4S |-| Pliny - OBLITERATUS | https://github.com/elder-plinius/OBLITERATUS |--| AgentShield | https://github.com/affaan-m/agentshield |-| McKinsey 聊天机器人被黑 (2026年3月) | https://www.theregister.com/2026/03/09/mckinsey\_ai\_chatbot\_hacked/ |-| AI 网络犯罪激增 1500% | https://www.hstoday.us/subject-matter-areas/cybersecurity/2026-global-threat-intelligence-report-highlights-rise-in-agentic-ai-cybercrime/ |-| ROME 事件 (阿里巴巴) | https://www.scworld.com/perspective/the-rome-incident-when-the-ai-agent-becomes-the-insider-threat |-| Dark Reading: 智能体攻击面 | https://www.darkreading.com/threat-intelligence/2026-agentic-ai-attack-surface-poster-child |-| SC World: 2026 年智能体漏洞事件 | https://www.scworld.com/feature/2026-ai-reckoning-agent-breaches-nhi-sprawl-deepfakes |-| AI-Infra-Guard (Tencent) | https://github.com/Tencent/AI-Infra-Guard |-| mcp-scan (Snyk / Invariant Labs) | https://github.com/invariantlabs-ai/mcp-scan |-| Agentic-Radar (SPLX-AI) | https://github.com/splx-ai/agentic-radar |-| OpenAI 收购 Promptfoo | https://x.com/OpenAI/status/2031052793835106753 |-| OpenAI: 设计能抵御提示注入的智能体 | https://x.com/OpenAI/status/2032069609483125083 |-| ZackKorman 谈智能体安全 | https://x.com/ZackKorman/status/2032124128191258833 |-| Perplexity Comet 被劫持 (Zenity Labs) | https://x.com/coraxnews/status/2032124128191258833 |-| 每 5 个 MCP 服务器中有 1 个滥用加密 (已审计 1,900 个) | https://x.com/TraderAegis |-| Snyk ToxicSkills 研究报告 | https://snyk.io/blog/prompt-injection-toxic-skills-agent-supply-chain/ |-| Cisco: OpenClaw 智能体是安全噩梦 | https://blogs.cisco.com/security/personal-ai-agents-like-openclaw-are-a-security-nightmare |-| 用于编码智能体的 Docker 沙盒 | https://www.docker.com/blog/docker-sandboxes-run-claude-code-and-other-coding-agents/ |-| Pliny - OBLITERATUS | https://x.com/elder\_plinius/status/2029317072765784156 |-| Moltbook 密钥在泄露后 5 周仍处于活动状态 | https://x.com/irl\_danB/status/2031389008576577610 |-| Nikil: "运行 OpenClaw 会让你被黑" | https://x.com/nikil/status/2026118683890970660 |-| NVIDIA: 沙盒化智能体工作流 | https://developer.nvidia.com/blog/practical-security-guidance-for-sandboxing-agentic-workflows/ |-| Perplexity Comet 被劫持 (Zenity Labs) | https://x.com/Prateektomar |-| 链接预览数据泄露向量 | https://www.scworld.com/news/ai-agents-vulnerable-to-data-leaks-via-malicious-link-previews |+| Check Point: Claude Code CVEs | <https://research.checkpoint.com/2026/rce-and-api-token-exfiltration-through-claude-code-project-files-cve-2025-59536/> |+| OWASP MCP Top 10 | <https://owasp.org/www-project-mcp-top-10/> |+| OWASP Agentic Applications Top 10 | <https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/> |+| Shannon AI (Keygraph) | <https://github.com/KeygraphHQ/shannon> |+| Pliny - L1B3RT4S | <https://github.com/elder-plinius/L1B3RT4S> |+| Pliny - CL4R1T4S | <https://github.com/elder-plinius/CL4R1T4S> |+| Pliny - OBLITERATUS | <https://github.com/elder-plinius/OBLITERATUS> |+| AgentShield | <https://github.com/affaan-m/agentshield> |+| McKinsey 聊天机器人被黑 (2026年3月) | <https://www.theregister.com/2026/03/09/mckinsey_ai_chatbot_hacked/> |+| AI 网络犯罪激增 1500% | <https://www.hstoday.us/subject-matter-areas/cybersecurity/2026-global-threat-intelligence-report-highlights-rise-in-agentic-ai-cybercrime/> |+| ROME 事件 (阿里巴巴) | <https://www.scworld.com/perspective/the-rome-incident-when-the-ai-agent-becomes-the-insider-threat> |+| Dark Reading: 智能体攻击面 | <https://www.darkreading.com/threat-intelligence/2026-agentic-ai-attack-surface-poster-child> |+| SC World: 2026 年智能体漏洞事件 | <https://www.scworld.com/feature/2026-ai-reckoning-agent-breaches-nhi-sprawl-deepfakes> |+| AI-Infra-Guard (Tencent) | <https://github.com/Tencent/AI-Infra-Guard> |+| mcp-scan (Snyk / Invariant Labs) | <https://github.com/invariantlabs-ai/mcp-scan> |+| Agentic-Radar (SPLX-AI) | <https://github.com/splx-ai/agentic-radar> |+| OpenAI 收购 Promptfoo | <https://x.com/OpenAI/status/2031052793835106753> |+| OpenAI: 设计能抵御提示注入的智能体 | <https://x.com/OpenAI/status/2032069609483125083> |+| ZackKorman 谈智能体安全 | <https://x.com/ZackKorman/status/2032124128191258833> |+| Perplexity Comet 被劫持 (Zenity Labs) | <https://x.com/coraxnews/status/2032124128191258833> |+| 每 5 个 MCP 服务器中有 1 个滥用加密 (已审计 1,900 个) | <https://x.com/TraderAegis> |+| Snyk ToxicSkills 研究报告 | <https://snyk.io/blog/prompt-injection-toxic-skills-agent-supply-chain/> |+| Cisco: OpenClaw 智能体是安全噩梦 | <https://blogs.cisco.com/security/personal-ai-agents-like-openclaw-are-a-security-nightmare> |+| 用于编码智能体的 Docker 沙盒 | <https://www.docker.com/blog/docker-sandboxes-run-claude-code-and-other-coding-agents/> |+| Pliny - OBLITERATUS | <https://x.com/elder_plinius/status/2029317072765784156> |+| Moltbook 密钥在泄露后 5 周仍处于活动状态 | <https://x.com/irl_danB/status/2031389008576577610> |+| Nikil: "运行 OpenClaw 会让你被黑" | <https://x.com/nikil/status/2026118683890970660> |+| NVIDIA: 沙盒化智能体工作流 | <https://developer.nvidia.com/blog/practical-security-guidance-for-sandboxing-agentic-workflows/> |+| Perplexity Comet 被劫持 (Zenity Labs) | <https://x.com/Prateektomar> |+| 链接预览数据泄露向量 | <https://www.scworld.com/news/ai-agents-vulnerable-to-data-leaks-via-malicious-link-previews> |***diff --git a/the-security-guide.md b/the-security-guide.mdindex 006639158..2f5b2425d 100644--- a/the-security-guide.md+++ b/the-security-guide.md@@ -447,7 +447,7 @@ Scan your setup: [github.com/affaan-m/agentshield](https://github.com/affaan-m/aIf you haven't read the previous guides, start here:> [The Shorthand Guide to Everything Claude Code](https://x.com/affaanmustafa/status/2012378465664745795)-+>> [The Longform Guide to Everything Claude Code](https://x.com/affaanmustafa/status/2014040193557471352)go do that and also save these repos: