dogear

enter for all results · esc to close

Inkog

inkog.iosite

AI agent security scanner. Detects behavioral vulnerabilities (prompt injection, infinite loops, token bombing, SQL injection via LLM) across 11 framework adapters including LangChain, CrewAI, and pydantic-ai. Audits MCP servers. Maps findings to EU AI Act, OWASP LLM Top 10…

from
Static Analysis & Code Quality
added
2026-10-10
likes
0

similar

  1. AIEngine bitbucket.org

    AIEngine is a next generation interactive/programmable Python/Ruby/Java/Lua packet inspection engine with capabilities of learning without any human intervention, NIDS(Network Intrusion Detection System) functionality, DNS domain classification, network collector, network…

  2. Ink inklestudios.com

    Scripting language for writing interactive narrative.

  3. ToxicSkills: Snyk Finds Malware and Prompt Injection in 36% of AI Agent Skills snyk.io

    Feb 2026 Snyk research across the ClawHub AI agent skills registry: 36% of audited skills contained security flaws, 1,467 malicious payloads found, and 2.9% used curl | bash remote instruction loading to evade static analysis. Covers indirect injection via poisoned web content…

  4. INK!athon inkathon.xyz

    Full-stack dApp boilerplate with ink! smart contracts and a React frontend using the useInkathon (listed below) hooks library maintained by Scio Labs.

  5. godot-ink github.com

    A C# (Mono) plugin to integrate stories writen in ink, a scripting language for writing interactive narrative.

  6. Prompt Injection 2.0: Hybrid AI Threats arxiv.org

    Jul 2025 paper showing how prompt injections now combine with XSS, CSRF, AI worm propagation, and multi-agent infections to evade traditional WAFs entirely. Evaluates Preamble's classifier, data-tagging, and RL-based defenses against these hybrid scenarios.

Static Analysis & Code Quality › Multiple languages: “AI agent security scanner. Detects behavioral vulnerabilities (prompt injection, infinite loops, token bombing, SQL injection via LLM) across 11 framework adapters including LangChain, CrewAI, and pydantic-ai. Audits MCP servers. Maps findings to EU AI Act, OWASP LLM Top 10…”