#prompt-injection

Security-First Agentic IDE Coding Harness

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

Zero-trust repo intake for AI coding agents — scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo. Ships its own false-negative ledger.

EvalBot — local-first chatbot security & quality evaluation (FastAPI + Next.js). Evaluate chatbot answers against your own docs & guidelines with ML/NLP + AI-judge scoring. Apache-2.0.

Codex Issue Radar and maintainer-readiness tooling for AI coding agents.

Attack taxonomy, toolkit & defenses for persistent-memory poisoning of LLM agents. Author: Krishita Sanjay Choksi.

AI-powered cybersecurity assistant for Prompt Injection and Phishing URL Detection.

A self-contained AI security lab demonstrating document poisoning, indirect prompt injection, and data exfiltration in RAG systems. Explores the "helpfulness paradox" across local and frontier LLMs.

An audit gate for AI agent outbound messaging: hold the draft, let a senior agent review it (no private-data leak, prompt-injection resistance), then release. Reference implementation.

seatbelt for my pi.dev agent: blocks secret-file access, redacts creds from output, blocks egress + git leaks.

AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy boundary, a tamper-evident audit log, and a human-in-the-loop approval cockpit. No kernel modules. Apache-2.0.

The authorization layer for AI agents — allow/deny/ask policy, human approvals, and tamper-evident receipts on every tool call. Zero-dep, framework-neutral, no SaaS.

Border Guard — AI-native territory sovereignty & self-evolving security OS. 6-module D-S fusion engine, trajectory detection, anchor detection, fission engine, territory adjudicator. Full design + Python implementation.

Lint Your Prompts, Ship Better Agents – Prompt Refiner 2026 Rule Engine

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

Drop-in middleware that detects AI bot traffic. Community-maintained signature database + RFC 9421 Web Bot Auth verification. Node + Python + Go. Apache-2.0.

Claude Code scaffold for building AI platforms securely — agent/LLM security, Kubernetes, SRE, observability, identity, and supply chain, grounded in published framework canon (OWASP, NIST, CIS, SLSA). Data-science lanes included.

Best AI Agent Skill Finder 2026 – Multi-Registry Install & Security Labels

Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

TokenFuse — runtime control for AI agents: per-run budgets, loop detection, burn forecast, kill-switch. Observability shows the fire; TokenFuse is the automatic extinguisher.

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

Static analysis for AI agents in GitHub Actions — finds where attacker-controlled text reaches an agent's prompt, and what that agent is allowed to do with it.

Curated research on AI agent social engineering, manipulated delegation, prompt injection, tool-use boundaries, and agent security evaluation.

Source-backed archive of agent prompt-injection incidents, research records, trust-boundary patterns, schemas, and sanitized defensive summaries.

A reproducible definition separating agent-directed manipulation from legitimate machine-readable self-presentation. Two mechanically decidable axes, 13 conformance cases.

Dark Promptery: 324 LLM prompt-injection techniques, crosswalked to OWASP/MITRE ATLAS/NIST/CWE.

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

Free AI-agent risk self-check, security checklist, and USD 59 launch-readiness mini-audit offer.

Trustworthy AI evaluation tool for testing chatbot safety, reliability, hallucination behavior, privacy risk, and instruction-following quality.

Claude Code slash commands that flag Unicode used outside string literals — a common prompt-injection / homoglyph vector

An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.

Hermes-inspired security control plane for LLM agents over private DMs: allowlist, PIN, kill switch, rate limits, injection heuristics, secret redaction, audit log.

LLM red-team evaluation harness — prompt injection, refusal, leakage and staleness, with cross-judge validation and attack-corpus audits.

An auditable, bounded mediation layer for Claude in Chrome browser actions — content-blind action gating, with its own failure map published.

Route coding tasks through an automated 8-agent pipeline for optimized, secure, and production-ready code output in Claude Code.

A policy hook for Claude Code

A JSON-RPC firewall for MCP agents — inspects every tools/call between an LLM and its MCP servers, blocking argument injection and capability creep before they reach the host.

Prompt Injection Guard - a defense-in-depth (rules + LLM) demo that detects and blocks prompt-injection / jailbreak attempts in LLM user input (Streamlit + Claude).

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.