credit score for context
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
Hardened security configuration for Claude Code; permission deny rules, shell hooks, and prompt injection defense in full and lite variants.
Multi-registry skill discovery and installation for AI coding agents — search 9 sources, score, paginate, and install agent skills with security labels
Governance guardrails and insights for AI coding agents
A Collection of Defensive Cyber Security skills designed to harden your Software, Infrastructure and even Game.
SpyAI scans targets looking for ports, HTTP banners, and API paths typical of LLM agents, RAG, vector stores, and adjacent infrastructure. No authentication, no fuzzing, no exploits.
A secure, agent-native GitHub repository template for Claude Code and Codex. Pre-commit secret checks, CI checks on pull requests, SHA-pinned Actions, CODEOWNERS on agent config files. MIT.
A security baseline for vibe coding with Claude Code: a CLAUDE.md that sets the rules, plus permissions, hooks and read-only subagents that enforce the parts a long session forgets.
Adversarial security review for AI skills, repos, MCP servers, and packages before you install them. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO WITH MITIGATIONS / NO-GO verdict.
Deterministic safety gates for repositories touched by coding agents and automation.
rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catch failures and vulnerabilities before they ship.
Sealed hidden daily achievements for team agents: anti-spam, prompt-injection safe, no retroactive awards.
Stop malware and supply-chain attacks before you git clone. AI-powered repo guard powered by Grok that detects fake stars, hidden risks, and shady repos.
SOSA™ — Supervised Orchestrated Secured Agents. A governance framework for production-grade autonomous AI operations.
Guardrails to stop data exfiltration from AI coding agents
Replicable agent development system: curated Claude Code/Codex skills + bootstrap for the external tools (GSD, caveman, ponytail) that complete the stack.
LLM and agent security skill pack for prompt injection, tool permissions, retrieval trust, memory poisoning, and context leaks.
Public verification, security review, and skill quality process for Agent Skill Exchange
Scan agent skills and plugins for malware and prompt injection before an agent loads them. Offline GitHub Action and CLI. The published projection of OpenTrApp's Skill Firewall.
To associate your repository with the prompt-injection topic, visit your repo's landing page and select "manage topics."