Search
Prompt injection and agent security
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 145 | Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against… | AnastasiyaW/ | 154 | — | ~764 | Automated safety check: Pass | MIT | yesterday |
| 146 | Apply Anthropic Claude API security best practices for key management, input validation, and prompt injection defense. | jeremylongshore/ | 2.8k | — | ~1.9k | Automated safety check: Notes | MIT | yesterday |
| 147 | Retell AI security basics — AI voice agent and phone call automation. | jeremylongshore/ | 2.8k | — | ~512 | Automated safety check: Pass | MIT | yesterday |
| 148 | Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks. | BagelHole/ | 1.2k | — | ~2.5k | Automated safety check: Pass | MIT | 4 mo ago |
| 149 | AI security papers from top-4 security conferences. An agent skill from wentorai/research-plugins. | wentorai/ | 298 | 1 repo | ~888 | Automated safety check: Pass | MIT | 3 mo ago |
| 150 | 150.Skill Scanner Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. | sundial-org/ | 663 | 1 repo | ~364 | Automated safety check: Pass | No licence | 7 mo ago |
| 151 | 151.Cot Injection 思维链 (Chain-of-Thought) 注入攻击方法论。当目标系统使用 ReAct/CoT 框架进行多步推理、 Agent 依赖中间推理结果做决策、或需要测试思维链完整性时触发。 | wgpsec/ | 1.8k | — | ~640 | Automated safety check: Pass | No licence | yesterday |
| 152 | 152.Review Pre-ship code review by a fresh-context Opus reviewer that checks the change against this project's hard rules — a false green, a channel rebuilt field by field, engine purity, schema versions… | guardana/ | 131 | — | ~315 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 153 | 153.Security Audit 2 Fail-closed security auditing for OpenClaw/ClawHub skills & repos: trufflehog secrets scanning, semgrep SAST, prompt-injection/persistence signals, and supply-chain hygiene checks before enabling or… | sundial-org/ | 663 | — | ~875 | Automated safety check: Pass | No licence | 7 mo ago |
| 154 | OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. | HoangNguyen0403/ | 572 | — | ~921 | Automated safety check: Pass | MIT | yesterday |
| 155 | 155.Security Copilot Guidance for Microsoft Security Copilot - the generative-AI security platform that helps analysts investigate, hunt, summarise, and respond using natural language, plugins, promptbooks, and embedded… | vinayaklatthe/ | 175 | — | ~1.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 156 | Guidance for Microsoft Security Copilot agents — autonomous, purpose-built AI agents (e.g., phishing triage, alert triage, conditional access optimization, vulnerability remediation) that work… | vinayaklatthe/ | 175 | — | ~2.1k | Automated safety check: Pass | MIT | 3 mo ago |
