Sandbox
170 repos for ai-agent · SecurityClear
ARPAHLS/
skillware
ARPAHLS/skillwareFrameworks & SDKs

A Python framework for modular, self-contained skill management for machines.

69
onecli/onecliHarnesses

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

3.5k

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

96
runxhq/
runx

the governed runtime for agent skill workflows, off the leash but on the record

84
netresearch/
security-audit-skill

Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible

41
orcasecurity/
orca-skills

Skills and plugins to accelerate security workflows with the Orca Cloud Platform

50
the-void-ia/
void-box
the-void-ia/void-boxFrameworks & SDKs

Composable agent runtime with enforced isolation boundaries

88
wshobson/
commands
wshobson/commandsRules & Prompts

A collection of production-ready slash commands for Claude Code

2.6k
Ido-Levi/
claude-code-tamagotchi

Real-time behavioral enforcement for Claude Code. Monitors AI actions, detects violations, and interrupts misbehavior. Also has a cute pet.

435
safedep/
gryph

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

161
Evol-ai/
SkillCompass

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

216
portofcontext/pctxFrameworks & SDKs

pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

274
google/
mcp-security

MCP servers for Google SecOps, GTI, SOAR, and SCC.

524
Gabson0x/
bountyforge

All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.

410
LuD1161/
agentjail

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

92
iammm0/
secbot

Authorized security testing workspace. v2 TypeScript terminal product on release; v1 Python on pypi-release; Go branch is demo only.

73
anton-abyzov/
vskill

Secure multi-platform AI skill installer — scan before you install. 49 agents, 12 plugins, 41 expert skills.

45
AIPentest/
CyberStrikeAI

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

6.5k

Privacy Code Scanner and Dataflow Context Engine for AI coding agents

130