Chained Harm & Injection Measurement for Evaluating Risks in Agents — a red-team research framework that tests hosted models, agentic apps, RAG pipelines, MCP servers, AI coding assistants, macOS desktop apps, and browser extensions against context-pollution, prompt-injection, and chain-composition attacks.
Cross-referenced across 55 tracked directories
#52225
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
4/28/2026
Created
1
GitHub Stars
6/28/2026
Last Commit
Recently added to the ecosystem
byteclawmail
MCP server for Wundervault zero-knowledge secret management
Sovereign encrypted persistent memory for AI agents. 8 MCP tools. GDPR erasure. Apache-2.0.
Pantani
Build real visual systems in TouchDesigner from plain language with Claude, Cursor or Codex.