Topic · Security

Best prompt injection and agent security skills, page 4

Skills #145–156 of 156, ranked by score.

Prompt injection and agent security skills, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Prompt injection and agent security skills, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
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/codex-claude-code-config154—~764Automated safety check: PassMITyesterday
146

Apply Anthropic Claude API security best practices for key management, input validation, and prompt injection defense.

jeremylongshore/tons-of-skills-marketplace2.8k—~1.9kAutomated safety check: NotesMITtoday
147

Retell AI security basics — AI voice agent and phone call automation.

jeremylongshore/tons-of-skills-marketplace2.8k—~512Automated safety check: PassMITtoday
148

Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.

BagelHole/DevOps-Security-Agent-Skills1.2k—~2.5kAutomated safety check: PassMIT4 mo ago
149

AI security papers from top-4 security conferences. An agent skill from wentorai/research-plugins.

wentorai/research-plugins2981 repo~888Automated safety check: PassMIT3 mo ago
150

Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them.

sundial-org/awesome-openclaw-skills6631 repo~364Automated safety check: PassNo licence7 mo ago
151

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/AboutSecurity1.8k—~640Automated safety check: PassNo licencetoday
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/guardana131—~315Automated safety check: PassApache-2.0today
153

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/awesome-openclaw-skills663—~875Automated safety check: PassNo licence7 mo ago
154

OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction.

HoangNguyen0403/agent-skills-standard572—~921Automated safety check: PassMITyesterday
155

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/microsoft-security-skills175—~1.8kAutomated safety check: PassMIT3 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/microsoft-security-skills175—~2.1kAutomated safety check: PassMIT3 mo ago