All tags
Catalogue tag

#tool-poisoning

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

6 records
Tagged “tool-poisoning”Ranked by health index
PyPI · npm
91Excellenthealth index
sattyamjjain/agent-audit-kit
Static scanner for MCP-connected AI agent pipelines. 348 rules across 14 categories, 14 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.
Python★ 13↓ 4,551/moSep 15, 2026
Apache-2.0Sep 15, 2026 · metrics 2.10.0
PyPI
89Excellenthealth index
mcp-hangar/mcp-hangar
MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.
Python★ 15↓ 2,905/moSep 21, 2026
MITSep 21, 2026 · metrics 2.10.0
PyPI
87Excellenthealth index
sattyamjjain/agent-airlock
A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.
Python★ 15↓ 3,569/moSep 18, 2026
Apache-2.0Sep 18, 2026 · metrics 2.10.0
npm
81Excellenthealth index
getmcpm/cli
MCP security guard + package manager. Block prompt injection, tool poisoning and rug-pulls in Model Context Protocol servers at runtime; trust-scored installs with Sigstore provenance for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and Gemini CLI. Local, deterministic, no LLM in the loop.
TypeScript★ 3↓ 3,980/moOct 22, 2026
MITOct 22, 2026 · metrics 2.10.0
npm
75Goodhealth index
panguard-ai/panguard-ai
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
TypeScript★ 65↓ 125/moOct 22, 2026
MITOct 22, 2026 · metrics 2.10.0
PyPI
73Goodhealth index
sunglasses-dev/sunglasses
Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.
Python★ 10↓ 1,856/moOct 19, 2026
MITOct 19, 2026 · metrics 2.10.0