tool-poisoning repositories

Trending repositories tagged tool-poisoning, ranked by trending score. Updated daily.

  1. 1
    panguard-ai/panguard-ai

    Open-source security for AI agents: scans skills and MCP servers before install and checks agent tool calls at runtime, on the open ATR rules. | AI agent 開源安全:安裝前掃描 skill 與 MCP server、執行期檢查工具呼叫,使用開放的 ATR 規則。

    GitHub · TypeScript · 69 stars · 12 forks · +2 stars in 24 hours · Trending score 0.95

  2. 2
    saurabh-yergattikar/ShieldMCP

    Transparent MCP security proxy: tool metadata integrity, call validation, and response analysis. Apache-2.0.

    GitHub · Python · 13 stars · 25 forks · +3 stars in 24 hours · Trending score 0.94

  3. 3
    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 1,566 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.

    GitHub · Python · 12 stars · 3 forks · +1 stars in 24 hours · Trending score 0.56

  4. 4
    Paraphern/rugsnare

    218 silent contract changes found in the npm MCP top. Pin MCP tool contracts, fail CI on drift. Zero deps, no telemetry, on-chain verified.

    GitHub · JavaScript · 6 stars · 4 forks · 0 stars in 24 hours · Trending score 0.19

  5. 5
    Ju571nK/lodeline

    Open-source config scanner for AI coding agents: scores the permissions, hooks, sandbox and MCP settings of Claude Code, Codex, Cursor and Gemini CLI. Runs locally and measures by default, with an optional fleet server and SIEM feed. Rust.

    GitHub · Rust · 17 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10

  6. 6
    garagon/aguara

    The open source security engine for AI agent and supply-chain trust.

    GitHub · Go · 94 stars · 16 forks · 0 stars in 24 hours · Trending score 0.04

  7. 7
    GT-Projects256/mcpguard

    Open-source security firewall for MCP servers. Scan for OWASP MCP Top 10 vulnerabilities, enforce runtime policies on AI agent tool calls, and generate compliance audit logs.

    GitHub · TypeScript · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    mcpware/IntentProbe

    CPU activation probes for AI-agent guardrails and classification. One frozen local model pass, many independent heads. Open models, code and reproducible benchmarks.

    GitHub · Python · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    alphaparkinc/genpark-mcp-tool-description-injection-and-exfiltration-scanner-skill

    Scans MCP tool schemas and descriptions for prompt injection, tool shadowing, and data exfiltration vectors

    GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    mcpware/cross-code-organizer

    Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

    GitHub · JavaScript · 395 stars · 34 forks · Trending score 0.09