GITHUB TOPIC
13projects include this topic
The "ai-security" topic on GitHub groups 13 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by SkillSpector with 17k GitHub stars. SkillSpector — Security scanner for AI agent skills. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
NVIDIA
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
pashov
Pashov Audit Group Skills
agamm
Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.
ptn1411
Bộ công cụ và tập hợp skill hỗ trợ phân tích phần mềm, khôi phục cấu trúc nguồn ở mức cần thiết, rà soát bảo mật, kiểm tra phụ thuộc và xây dựng kế hoạch khắc phục cho các hệ thống mà bạn sở hữu hoặc được phép đánh giá.
KongFangXun
sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 25 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 11 plugins). Everything can be FDEing.
Farenhytee
Claude Skill that audits your projects for RLS misconfigurations, exposed keys, auth bypasses, and storage vulnerabilities. 27 anti-patterns sourced from CVE-2025-48757 and 10 security studies. Safe for production.
unStone
X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.
lonelymoon87
Runtime tool policy, dangerous-command guard, and output redaction for DeepSeek Harness.
dingge001
DSH / DeepSeek Harness plugin: runtime secret & PII redaction with mask, reversible vault and execution-time substitution
ishamishra0408
A teammate posts one Slack message. Your AI assistant reads it, believes it, and hands over your keys through a link preview — nothing shows in the channel. Three plugins for the dsh agent harness stop the message before it leaves. Live demo you can run: real detectors, a real model as the victim.
lukethecat
This repository does not yet provide a project description.
ramen-ai-dev
Pre-execution semantic firewall for AI agents. Signed policy verdicts, BYOK, zero-trust receipts.
sashankh
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin, gates privileged calls that follow untrusted content, and refuses credentials heading off the machine.