agent-plugins
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
No outside reports on file
This plugin gives your AI agent real power over your AWS account, so use restricted credentials, monitor all actions, and keep the code up-to-date from trusted sources.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (awslabs/agent-plugins)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/awslabs/agent-plugins ↗
About Agent Plugins
Agent Plugins for AWS gives AI coding agents (like Claude) the ability to build, deploy, and manage applications on Amazon Web Services. It connects your AI assistant to AWS tools so it can help you make infrastructure decisions and automate cloud operations.
Who it’s for
Software developers and DevOps teams who want AI coding assistants to help with AWS architecture, deployment, and troubleshooting. Best for teams already using AWS and AI agents together.
Alternatives
- AWS CDK (Construct Development Kit): Write infrastructure as code in Python or JavaScript without an AI intermediary.
- Terraform with LLM integrations: Some teams use ChatGPT or Claude plugins with Terraform for managed infrastructure.
- AWS Well-Architected Tool: AWS's own service to review and improve cloud architecture without AI agents.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. The setup likely involves configuring AWS credentials and connecting the plugin to your AI agent framework, but specific installation steps should be verified in the official repository.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 932
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- AWS account access: The agent gains permissions to create, modify, or delete AWS resources based on your configured credentials—malicious instructions could cost money or expose infrastructure.
- Over-privileged keys: If AWS access keys are too permissive, the agent can do more damage than intended, even by accident.
- Prompt injection: An attacker could embed hidden instructions in error messages or AWS API responses that trick the agent into running unintended commands.
- Data exposure: Logs, configuration details, or sensitive information from your AWS environment could leak if the AI agent outputs them unsafely.
- Supply chain trust: Changes to this GitHub repository could introduce malicious code; verify updates before deploying to production.
How to lower the risk
Least-privilege permissions
- Create an IAM role with only the AWS actions your AI agent truly needs.
- Avoid using root or admin credentials; use temporary tokens with short expiration times.
Network isolation
- Run the agent in a private VPC or restricted network when possible.
- Use AWS security groups to limit what the agent can reach.
Monitoring
- Enable CloudTrail to log every API call the agent makes.
- Set up alerts for unusual or high-cost AWS operations.
Red flags to watch for
- Agent suddenly requesting permissions it didn't need before.
- Unexpected AWS charges or resource creation you didn't authorize.
- Error messages that seem suspicious or ask the agent to bypass security checks.
Questions
How do I install Agent Plugins?
Agent Plugins does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/awslabs/agent-plugins.
Are there security reports about Agent Plugins?
No reports found for this package in our research (last checked 2026-10-29). Agent Plugins currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include aws account access, over-privileged keys, prompt injection.
Is Agent Plugins actively maintained?
Agent Plugins has 932 GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/awslabs/agent-plugins before pinning it in production.
What are alternatives to Agent Plugins?
Notable alternatives to Agent Plugins include AWS CDK, Terraform with LLM integrations (Some teams use ChatGPT or Claude plugins with Terraform for managed infrastructure), AWS Well-Architected Tool (AWS's own service to review and improve cloud architecture without AI agents). You can also compare Agent Plugins side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Agent Plugins? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/awslabs-agent-plugins)HTML embed:
<a href="https://agentarmorhq.com/skills/awslabs-agent-plugins"><img src="https://agentarmorhq.com/api/badge/awslabs-agent-plugins" alt="AgentArmorHQ Risk Grade for Agent Plugins" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "awslabs-agent-plugins"Share with your security lead
Need sign-off to use agent-plugins? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: agent-plugins
- **Listing URL:** https://agentarmorhq.com/skills/awslabs-agent-plugins
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 932 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (awslabs/agent-plugins)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/awslabs/agent-plugins
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- awslabs
- Source code
- github.com/awslabs/agent-plugins
- Est. context load
- ~55 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 932 GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-23
Community
Discussions for Agent Plugins
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude