Agent Scan
PulseGate's liveness check found it on 13 Sep 2026; it is registered on GitHub and has been in the index since 13 Sep 2026. How this is checked
Agent Scan Skill Inspector analyzes agent skills for malicious behavior and security vulnerabilities before installation. Its web interface accepts skill folders, while the Snyk Agent Scan CLI scans local agents, MCP servers, and skills across supported agent environments.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing malicious skills and agent supply-chain vulnerabilities from being installed or deployed.
Inferred · not functionally tested
Audience: AI agent developers and security teams
Inferred · not functionally tested
Functions: monitoring, data_extraction
Inferred · not functionally tested
Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown
Recorded constraints: pricing: free · license: Apache-2.0 · platforms: WEB · deployment: browser, cli, cloud_managed
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: labs.snyk.io · github.com. These links do not verify the individual claims.
In the AI security & guardrails space, Agent Scan takes a focused approach. Inferred · not functionally tested: It focuses on preventing malicious skills and agent supply-chain vulnerabilities from being installed or deployed. Inferred · not functionally tested: Agent Scan is a B2B product aimed at AI agent developers and security teams. Basis unknown · not verified: Agent Scan costs nothing to use. Basis unknown · not verified: It runs on the web and the command line.
It is developed by Snyk, and it first shipped in 2025. Development happens publicly on GitHub with 3k stars and 145 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are skill scanning, MCP scanning, and prompt injection detection. Basis unknown · not verified: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Skill scanning
- MCP scanning
- Prompt injection detection
- Tool poisoning detection
- Toxic flow detection
- Folder upload
Topics: Inferred · not functionally tested
Built with & integrations
- Cursor
- commit fb6967552753 · since Aug 2026
- Next.js
- x-nextjs-prerender header · /_next/static/ in the HTML · __next_f in the HTML
- Vercel
- x-vercel-id header · x-vercel-cache header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed13 Sep · 02:37 UTCAgent Scan Skill Inspector seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about Agent Scan
- What does Agent Scan do?
- Inferred · not functionally tested: Agent Scan focuses on preventing malicious skills and agent supply-chain vulnerabilities from being installed or deployed. It is catalogued under AI security & guardrails on PulseGate.
- Who is Agent Scan for?
- Inferred · not functionally tested: Agent Scan is a B2B product built for AI agent developers and security teams.
- Is Agent Scan free?
- Basis unknown · not verified: Yes — Agent Scan is free to use.
- What platforms does Agent Scan run on?
- Basis unknown · not verified: Agent Scan runs on the web and the command line.
- Is Agent Scan still maintained?
- PulseGate's liveness check found it on 13 Sep 2026. Its GitHub repository shows 145 commits in the last 90 days.
- What are alternatives to Agent Scan?
- Similar projects tracked by PulseGate include Agent Scan, SkillScan, and agent-skill-scanner.Agent ScanSkillScanagent-skill-scanner
- Who makes Agent Scan?
- Agent Scan is developed by Snyk.
- When did Agent Scan launch?
- Agent Scan first shipped in 2025.
Similar projects
Closest matches by what these projects do