📄 skillActivePromisingmedium
harness
Harness is an AI Agent development guardrail Meta-Skill that establishes four layers of defense for any project in one command: knowledge management, architecture constraints, feedback loops, and entropy management.
Supported Platforms
🤖 Claude Code
Quality Breakdown
115/ 200
Content Signals
Repo Health
Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.
Trust & Verification
medium
Requires extended permissions (shell access, subagents). Review before use.
Active
Updated within the last 90 days. Actively maintained.
Risk Assessment
- Contains exploit scripts and POC templates (exploit.sh, poc.html) in android-vuln-analyzer bundled skill
- Includes offensive security content: vulnerability hunting guides, taint analysis, bypass strategies, POC generation references
- Bundled skill for android vulnerability analysis with CVSS scoring and exploit examples
- Setup scripts present (setup_environment.sh) that could modify system state
- Framework references for common attack vectors (SQL injection, path traversal, webview vulnerabilities, deeplink hijacking)
- References to penetration testing and security assessment capabilities without clear authorization gates