by avast · Claude Skill · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
/plugin marketplace add https://github.com/gendigitalinc/sage.git
/plugin install sage@sageTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 119 |
| Forks | 5 |
| Language | TypeScript |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 68/100 |
| Open Issues | 3 |
| Last Updated | 2026-03-10 |
| Created | 2026-02-12 |
| Platforms | browser, claude-code, node, vscode |
| Est. Tokens | ~205k |
Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layers before they run.
Looking for a sage alternative? If you're comparing sage with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. P
The Complete AI Development Toolkit for Claude Code. 115 skills, 36 agents, 161 hooks. Install `ork` for stabl
Leash by StrongDM - take your AI agents for a walk
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.
Release channel for TheAuditor — see blog.theauditortool.com
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: