27 tagged prompt injection, measured the same way as everything else here.
Browse within: ai-security 12devsecops 5llm-security 5
Instructions file
Instructions for romovpa/claudini, covering claudini — developer guide, package manager, running benchmarks, run a preset (all methods, all samples) and override method, sample, seed, budget from cli.
Instructions file CodexOpenCode
Instructions for garagon/aguara, covering agents.md - aguara reference for ai agents, quick start, install, scan a directory and scan with ci defaults (fail on high+, no color).
Instructions file
Instructions for garagon/aguara, covering claude.md, project status, build & test commands, single package test and single test function.
Instructions file
Project instructions for Aigis, a setup that manages Zenn articles and books through GitHub. Zenn is a publishing platform for developer articles and books.
Instructions file
Instructions for dwarvesf/claude-guardrails, covering claude.md, what this repo is, architecture and key design decisions.
GSA-TTS/agentic-coding-playbook
Instructions file CodexOpenCode
Best practices for AI coding agent behavior in federal development environments — includes behavioral standards, engineering discipline enforcement, and verification requirements.
AgentSafe-AI/tooltrust-scanner
Instructions file
Instructions for AgentSafe-AI/tooltrust-scanner: Use the /browse skill from gstack for all web browsing. Never use mcpclaude-in-chrome tools.
Instructions file
Instructions for akanthed/SecureAI-Scan, covering claude.md, what this is, hard requirements (non-negotiable, apply to every change), 1. zero tolerance for false positives and commands.
Instructions file
Instructions for sinewaveai/prooflayer-rules, covering claude.md, project overview, development commands, installation and install in development mode.
Instructions file
Instructions for adamsjack711-ux/pkgxray, covering project, rules, skills, getting started and commands.
Instructions file
Instructions for Sanexxxx777/evidence-to-skill, covering project guidance, boundaries and required verification.
Instructions file CodexOpenCode
Instructions for swnotmetal/Project-Koma, covering koma — ai coding agent rules, when to use koma, quick integration, design rules and package overview.
hugobatista/copilot-instructions-unicode-injection
Instructions file GitHub Copilot
Copilot instructions for hugobatista/copilot-instructions-unicode-injection, a project described as: Proof of Concept (PoC) demonstrating prompt injection vulnerability in AI code assistants (like Copilot) using hidden Unicode characters within instruction files (copilot-instructions.md). Highlights risks of using…
Instructions file CodexOpenCode
Instructions for meghal86/promptsonar, covering promptsonar agent instructions, operating principles, repo layout, common commands and change workflow.
Instructions file
Instructions for meghal86/promptsonar, covering claude code instructions, promptsonar, structure, key functions and conventions.
Instructions file
Claude Code instructions for zakariaf/SecScanMCP, covering claude.md, essential commands, development & testing, direct python usage and tool setup.
Instructions file
Claude Code instructions for snapsynapse/guidecheck, covering claude.md, purpose, tech stack, directory layout and conventions.
Instructions file
Claude Code instructions for DeepScan-Security/dscan, covering dscan — claude code instructions, workflow rules, tdd rules, code style and what not to do.
Instructions file
Claude Code instructions for akar5h/jakk, covering jakk — agent guidance, repo orientation, probe library policy (load-bearing), active project — fastmcp ecosystem audit and engineering conventions.
Instructions file CodexOpenCode
Instructions for decoy-run/decoy-redteam, covering decoy-redteam — agent reference, what this tool does, architecture, attack categories and safety model.
Instructions file
Instructions for adudley78/mcp-audit, covering mcp-audit, what this project does, business model, tech stack and project layout.
Instructions file CodexOpenCode
Instructions for shisa-ai/textguard, covering textguard agent guide, current source of truth, first principles, intended project shape and working rules.
Instructions file
Instructions for shisa-ai/textguard, a project described as: Hostile-text normalization, inspection, and cleaning for LLM-adjacent systems.
Instructions file
Claude Code instructions for enchanter-ai/cyclops, covering cyclops — agent contract, hard invariants, layout, downstream servers and ship bar.