Correctover
@dshcorrectover
Architecture-level security analysis of public AI inference & agent frameworks. Evidence-grade, hash-anchored. SCITT/SAMP/IETF I-D work.
8
Published Tools
3
Total Stars
6
Weekly Downloads
0
GitHub Followers
41
Public Repos
99/100
Avg Security
Published Tools
7 MCP Servers1 Agentacross 3 categoriesDSHCorrectover
Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
DSHCorrectover
CCS Runtime Evidence MCP Server
Correctover <[email protected]>
Cryptographic runtime receipts for MCP servers and clients — signed Ed25519 audit evidence for every tool call.
Cryptographic runtime receipts for CrewAI agents — signed Ed25519 audit evidence for every tool call.
Cryptographic runtime receipts for LangChain/LangGraph agents — signed Ed25519 audit evidence for every tool call.
Cryptographic runtime receipts for Microsoft AutoGen agents — signed Ed25519 audit evidence for every tool call.
Cryptographic runtime receipts for OpenAI Agents SDK — signed Ed25519 audit evidence for every tool call.
Independent fail-closed second fuse for AI agents: runtime guard + signed receipts + incident reports