security-preflight
v1.3.1
io.github.jdhart81/security-preflight
Static MCP, source-code and injection-indicator checks with redacted signed receipts.
“Prompt Injection” 共 260 个结果
v1.3.1
io.github.jdhart81/security-preflight
Static MCP, source-code and injection-indicator checks with redacted signed receipts.
v0.1.0
net.agentglass/agentglass
Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
v1.0.0
com.edgethirteen.www/site-audit
Discover a site's pages from its sitemap and sample them for WCAG and prompt-injection risk.
v1.0.0
io.github.Ansarii/mcp-security-auditor
Static AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.
v0.2.0
io.github.gaurav-kumar-sinha-060705/singularity
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
v0.3.18
io.github.maginaryai/maginary-mcp
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
v0.11.3
io.github.AIops-tools/ai-guardian
受治理的本地 LLM 可观测性:模型策略、提示词扫描、捕获代理,21 个工具。
v1.1.0
com.transcodely/mcp
一条提示即可转码、托管并为视频加字幕。15 个工具,其中 9 个只读,绝不删除内容。
v1.0.0
dev.workers.manhliemcn4euwlu.llmrt-companion/llm-red-team-scanner
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
v4.1.1
io.github.upstash/context7
为任意提示词提供最新的代码文档。
v0.3.1
io.github.vikasny30/aletheia-mcp
Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
v1.0.0
app.vercel.cloakcheck-wheat/cloakcheck
Scan a page for hidden prompt-injection payloads targeting AI agents.
v0.3.0
io.github.dreamor/memvault
Shared memory router for AI agents: save/search/recall, session-start injection, review inbox.
v1.0.9
io.github.VineetV2/peon-mem
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
v1.0.0
io.github.BuilderIO/agent-native-analytics
Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
v0.14.0
io.github.shinpr/mcp-image
AI 图像生成与编辑,支持提示词优化与质量预设。
v1.2.0
com.moltlinestudio/govern
审计 MCP 配置与技能文件,发现权限过宽与注入风险,8 个工具中 6 个免费。
v0.1.0
io.github.entradox/trust-scan
Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.
v0.0.1
io.github.kadopi/guardrail-mcp
Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
v0.2.9
io.github.RolloutsAI/mails-agent-email
A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
v1.24.0
club.worldorder/protocol-gym
免费的 AI 智能体挑战赛,提供 MCP 提示、资源、免身份认证评测、提示与回放。
v1.0.0
ai.routing24/mcp
配送车队的路径优化:用提示词规划、编辑并重新优化多站点路线。
v0.2.0
io.github.adamVass/pylos-mcp
Read-focused, prompt-injection-hardened email MCP server for any IMAP provider
v1.0.1
com.mcpscores/web-extract
把任意网页读成可用于提示词的干净文本,或列出其中全部链接。