44 tagged llm-security, measured the same way as everything else here.
Browse within: ai-security 27agent-security 12Prompt Injection 5devsecops 5model-context-protocol 5
Instructions file CodexOpenCode
Instructions for subodhkc/ai-appsec, covering agents.md — haiec agent security mcp (phase -1 → phase 18), 1. workspace layout, 2. architectural principles (apply to every phase), 3. hard constraints (never violate) and 4. phase discipline.
Instructions file CodexOpenCode
Instructions for BashaarJavaid/MCP-Sentinel, covering agents.md, project, where things live, conventions and commands.
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 CodexOpenCode
A repository instruction file for Codex, describing how to work on Sieve, a local Rust program that checks traffic between AI coding agents and language models before sensitive crypto actions.
Instructions file
Repository instructions for Sieve, a local program that sits between coding agents and AI model services to check traffic and risky crypto actions. They define the project's current state, authoritative documents, and rules that changes must follow.
Instructions file
Instructions for v0idw4lker/trustmcp, a project described as: Free, open-source security scanner for MCP servers, static analysis, live dynamic probing, auth posture detection, and SARIF/JSON reporting with A-F scoring mapped to OWASP MCP Top 10.
Instructions file
Claude Code instructions for kenithphilip/Tessera, covering claude.md, what this project is, threat model (narrow on purpose), load-bearing invariants that must not be weakened and tessera vs agentmesh.
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
Project instructions for AgentToolGate, a local gateway that governs AI tool calls and local hook actions through policies, approvals, secret handling, and audit records.
Instructions file
Project instructions for AgentToolGate, a local gateway that governs AI-agent tool calls using policies, approvals, audit records, and MCP connections. MCP is a protocol for connecting agents to external tools and data.
Instructions file
Claude Code instructions for pezhik/skilltotal, covering claude.md, project, commands, install (editable) + dev deps and run one test file / one test.
Instructions file CodexOpenCode
AGENTS.md instructions for sanjoy1234/gauntlex, covering agents.md, what this project is, setup, running the test suite and key cli commands an agent will typically need.
Instructions file CodexOpenCode
AGENTS.md instructions for ilyautov/cordon, covering working in this repository, the three invariants, the map, commands and tests.
Instructions file
Claude Code instructions for bch1212/queryshield, covering queryshield — claude code context, what this is, architecture, critical rules and pricing tiers (models.tierlimits).
Instructions file
Claude Code instructions for kimss-ai/kimss-python-sdk: Read AIINTEGRATION.md (canonical public: kimss-control-plane).
Instructions file CodexOpenCode
AGENTS.md instructions for BackBond/agent-scan: Run npx -y @backbond/[email protected] vet-tools --stdin < tools-list.json before attaching an unfamiliar proposed toolset. Run npx -y @backbond/[email protected] scan for the broader environment scan. In a network-isolated environment, use the operator-staged…
Instructions file
Claude Code instructions for codeit-ronit/SENTINEL, covering claude.md — sentinel, what this project is, hard rules — violating any of these is a build failure, research before implementing and working style.
Instructions file CodexOpenCode
AGENTS.md instructions for AaronVick/AGENT_FABLES, covering agent fables, offline agent routes, failure reference and developer note.
Instructions file CodexOpenCode
AGENTS.md instructions for noguerol/cancerbero, covering agents.md — how ai agents should use cancerbero, 1. when to use cancerbero, 2. how to talk to cancerbero, 2.1 mcp server and 2.2 json-schema tools (non-mcp clients).
Instructions file
Claude Code instructions for kirandevihosur74/mcp-sentinel, covering claude.md, what this is, rules, bright data scraper configuration and registries.