AgentSeal/agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

57
/ 100
Established

This tool helps AI engineers and security professionals keep their AI agents safe from attacks. It scans your machine for dangerous configurations, monitors for malicious updates to agent skills and tool descriptions, and tests your AI agent's system prompts against known adversarial attacks. You input agent configurations, live MCP servers, or system prompts, and it outputs a security report with a trust score and details on detected threats.

119 stars. Available on PyPI.

Use this if you are building or deploying AI agents and need to ensure they are secure against prompt injection, supply chain attacks, or malicious tool poisoning.

Not ideal if you are looking for a general-purpose cybersecurity scanner for traditional software, as this tool is specifically designed for AI agent security.

AI-security agent-safety prompt-engineering supply-chain-security model-context-protocol
Maintenance 10 / 25
Adoption 10 / 25
Maturity 20 / 25
Community 17 / 25

How are scores calculated?

Stars

119

Forks

19

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/AgentSeal/agentseal"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.