LLM Security Scanner: Red-Team, Jailbreak, Prompt Injection Audit
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
ค้นด้วยงานที่อยากทำหรือชื่อโปรแกรม แล้วกรองตามหมวด
เรียงตามจำนวนคำค้นที่เจอในชื่อ คำอธิบาย และหมวด แล้วตามด้วยดาว
อ่านการ์ด:↓ ดาวน์โหลดต่อสัปดาห์i★ ดาว GitHubiสามเสา: รีวิว · ผลตรวจ · การใช้งานiอัปเดต = วันที่ส่งรุ่นล่าสุดเข้า registryi
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
7-chain EVM audits, log simulator, wallet due diligence, calldata decoder, Chainlink & ENS.
XFA device security, read-only: which devices pass their checks or have known vulnerabilities.
Free Slither scan of Solidity contracts for AI coding agents; optional paid report (1 USDC, x402).
A secret store for AI agents: the agent never sees the plaintext.
Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.
Audit on-chain DEX token liquidity pairs, volume, price action, and FDV via DexScreener.
Runtime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.
Zero-log MCP server with 49 tools for AI guardrails, secret scanning, MCP linting & EU compliance.
Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
Bounded local MCP access to one approved repository for AI read/search and structured handoffs.
Sandbox workspace tools: search, file read, DB queries, integrations. Returns synthetic data.
SPF, DKIM, DMARC, MTA-STS, DNSSEC, TLS and DNS checks for domains, with an API key or USDC (x402)
Guardrails for AI-written JS/TS: scans, weakened-test checks, package checks, verify before done.
The dependency bloodhound for AI coding agents. Zero API keys, zero config.
Research honeypot. Logs connections and tool arguments; injects instructions. Read README first.
Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-c.
Point Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools.
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
Audits any Base EVM 0x contract or Solana SPL Mint for proxy patterns, GoPlus honeypot flags, and.
Routes each task to the few skills, MCP servers and tools that fit it.