by codescan-ai · Agent Tool · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install codescanai
git clone https://github.com/codescan-ai/codescan.gitTaken 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 | 65 |
| Forks | 6 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 75/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-17 |
| Created | 2024-08-25 |
| Platforms | gemini, python |
| Est. Tokens | ~8k |
CodeScanAI CodeScanAI utilizes a variety of AI models to scan your codebase for security vulnerabilities. It leverages powerful LLM models to identify risks and provide actionable remediation suggestions. The currently supported AI providers include: OpenAI, Google Gemini, and custom self-hosted AI servers (Ollama, etc.).
These tools work well together with codescan for enhanced workflows:
Looking for a codescan alternative? If you're comparing codescan with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Lightweight agent orchestration dev tool that lives in your repo
MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
Static Code Analysis for security teams with Inter file taint analysis. Built for finding vulnerabilities, adv
Run AI coding agents in hardened container sandboxes.
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Explore other popular agent tool 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: