ai-vulnerability-trackerAI 漏洞追踪器 - 在 GitHub 和微信公众号搜索近一个月的 AI 相关漏洞(提示词注入、提示词越狱等),并推送到飞书表格。支持去重和翻译。 搜索关键字: prompt injection, prompt jailbreak, LLM vulnerability, AI security, adversar...
Install via ClawdBot CLI:
clawdbot install 0ctday/ai-vulnerability-trackerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://weixin.sogou.com/weixin?type=2&query=${encodeURIComponent(keywordUses known external API (expected, informational)
api.github.comAudited Apr 18, 2026 · audit v1.0
Generated Aug 23, 2026
Enterprises with AI applications can use this skill to stay updated on the latest AI vulnerabilities like prompt injection and jailbreaks. It automates the search across GitHub and WeChat public accounts, translates relevant content, and pushes updates to Feishu for team visibility.
Security researchers can leverage this tool to collect and consolidate AI vulnerability data from multiple sources. The deduplication and translation features streamline the process of identifying emerging threats and trends in AI security.
Organizations needing to comply with AI safety regulations can use this skill to monitor for vulnerabilities that may affect their products. It supports proactive risk assessment by providing timely alerts about relevant security issues.
Development teams can integrate this tracker into their CI/CD pipeline to receive weekly updates on AI security vulnerabilities. This helps in incorporating security fixes early in the development lifecycle and maintaining secure AI deployments.
Offer as a subscription service where clients receive regular AI vulnerability reports and alerts. The skill's automation reduces manual effort and provides value in proactive security posture.
Use the skill to gather data for consulting engagements focused on AI security assessments. The collected intelligence informs recommendations and helps clients remediate vulnerabilities.
Use internally to streamline security operations, reducing time spent on manual monitoring. This improves efficiency and reduces labor costs associated with threat tracking.
💬 Integration Tip
To integrate, ensure you have the required API credentials for GitHub, WeChat, and Feishu. Start by running manually to test, then set up cron jobs for scheduled execution.
Scored Jul 2, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Senior SecOps engineer skill for application security, vulnerability management, compliance verification, and secure development practices. Runs SAST/DAST sc...