GITHUB TOPIC
22projects include this topic
The "agent-security" topic on GitHub groups 22 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.
MicroMilo
Always-on compatibility testing for DeepSeek Harness plugins: exact releases, isolated runners, and fixable upstream issues.
agentic-control-plane
Agentic Control Plane for DeepSeek Harness — policy-check every tool call before it runs
Chhlafiu4312
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness.
unStone
X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.
rrrrrredy
Static security scanner for agent skills: A-F risk rating, safe zip scanning, CI-tested rules
AgentValet
Governed platform access for DeepSeek Harness. Brokered credentials, owner-side approval, no API keys on the machine.
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.
jhckevin
Codex-style Auto Review inspired plugin for DeepSeek Harness, with native bridge and Linux sandbox integration
kakapengta
A standalone security-check plugin that links directly to a DeepSeek Harness (DSH) Web profile. Before installing or using an untrusted Skill, run a local browser rough check first, then let the user decide whether to call the DSH-configured LLM for structured review.
ramen-ai-dev
Pre-execution semantic firewall for AI agents. Signed policy verdicts, BYOK, zero-trust receipts.
unStone
Ask what a DeepSeek Harness plugin can actually do, from inside your agent. Companion to dsh-xray.
zephaniahwang94-cmyk
Authentication and security hardening plugin for DeepSeek Harness
DSHCorrectover
CCS Runtime Verifier Skill — 7-dimension runtime verification for MCP tool calls. Structure, Schema, Latency, Cost, Identity, Integrity, Security checks.
guhanfei-ai
Cryptographically bind human authorization to the exact action an AI agent is about to execute.
julescules
DeepSeek Harness safety guard for PowerShell and structured file edits on Windows.
MangShe3-0
Offline-first security scanner for DeepSeek Harness plugins: prompt injection, ransomware, exfiltration, and supply-chain risks.
okaditya84
Security guard plugin for DeepSeek Harness: secret redaction, a shell command denylist, prompt-injection scanning, and syntax verification.
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.
scodypanda
This repository does not yet provide a project description.
Top-Celestial-Company-Ltd
⚡ DROS™ VajraClaw for DSH: Deterministic Runtime Execution Governance & Security Circuit-Breaker Plugin