whereismyai
Snyk Agent Scan
Snyk Agent Scan: Security scanner for AI agents, Model Context Protocol servers and agent skills.
Agent Scan discovers installed agent components and scans them for common threats like prompt injections, sensitive data handling, or malware payloads. It supports Model Context Protocol servers, agent tools, prompts, resources, and skills across multiple operating systems. Users can run the tool via uvx or by downloading a standalone binary from GitHub Releases. It automatically detects agent configurations such as Claude Code, Claude Desktop, Cursor, Gemini CLI, and Windsurf. Users require a Snyk API token to run scans.
Snyk Agent Scan at a glance
- Best for: Software engineer
- Runs on: macOS, Linux, Windows, CLI
- Pricing: Free
- Released: April 2025
- Category: AI coding tool
- Website: github.com/snyk/agent-scan
Key features
- Auto-discover Model Context Protocol configurations, agent tools, and skills
- Detect prompt injections and vulnerabilities
- Scan Claude, Cursor, GitHub Copilot, Windsurf, Gemini CLI, and other agents
- Run via uvx or standalone binary
- Support system, user, project, and extension scopes
Use it for
- Discover installed agent components on a machine
- Scan Model Context Protocol servers and agent skills for prompt injections
- Identify malware payloads hidden in natural language
Alternatives to Snyk Agent Scan
- Stroq — Scans recorded sessions and guards future actions with local hooks.
- Runway — Control Claude Code and Codex sessions on local or cloud machines from any phone.
- ModVet — Scans Claude Code mods offline in milliseconds with zero dependencies.
- Cisco Skill Scanner — Combines pattern matching, dataflow analysis, and an optional LLM judge for threat detection.
- Claude BugHunter — It loads 83 skills and 15 slash commands automatically by topic.
- SkillTotal — Scans code locally without accounts, telemetry, API tokens or executing the files.
- Claude Code Router — It centralizes control of AI agent requests with intelligent routing and observability.
- Claude Tap — Inspect prompts, tool calls, and token usage locally without a hosted dashboard.
- Claude Super Sidebar — It brings agent relationships, execution states, and task flows into one panel.
- Agentic Bug Hunter — It drives the reconnaissance, triage and reporting loop an agent would run.
- Rashomon — Verifies whether Claude Code actually completed tasks or hid command failures.
- Tstack — Automates complex pull request workflows and multi-model code reviews.
All Snyk Agent Scan alternatives