terrashark
Terraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It eliminates hallucinations, is designed for modular and secure code and grounds your IaC in the official Hashicorp Terraform best practices.
No outside reports on file
Use this skill only with non-sensitive test infrastructure and always review generated code for security issues before deploying to production.
Based on public adoption and transparency signals as of Oct 27, 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 (LukasNiessen/terrashark)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/LukasNiessen/terrashark ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-27.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Terrashark
TerraShark is a skill that helps AI language models write Terraform code (infrastructure-as-code) more accurately. It reduces hallucinations—when AI makes up fake Terraform commands or syntax—by grounding responses in official HashiCorp best practices and focusing on modular, secure code patterns.
Who it’s for
Developers and DevOps engineers who use Claude or similar AI tools to generate Terraform infrastructure code. Teams that want to reduce errors and security issues in their cloud infrastructure setup.
Alternatives
- Terraform official documentation and examples: Manual reference alongside AI.
- Checkov: Open-source tool that scans Terraform for security and compliance issues.
- tflint: Linter that catches Terraform errors and bad practices before deployment.
- Snyk Infrastructure as Code: Scans and fixes infrastructure code for vulnerabilities.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/LukasNiessen/terrashark (opens external site) for installation instructions specific to your AI tool (Claude Code or Codex).
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
- 714
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Cloud credentials exposure: If the AI reads your Terraform files during setup, it could see AWS keys, Azure tokens, or other secrets hardcoded in those files.
- Malicious Terraform templates: If someone tricks the skill by providing fake Terraform examples as "best practices," the AI might generate infrastructure code that opens security holes.
- Unvalidated code generation: The skill may still produce Terraform that looks correct but doesn't work, potentially creating unexpected cloud resources or costs.
- Data leakage in prompts: Details about your infrastructure (project names, IP ranges, database names) shared in AI prompts could be logged or retained.
- Version mismatches: Generated code might use outdated Terraform provider versions that have known vulnerabilities.
How to lower the risk
Least-privilege permissions
- Never store real AWS keys or cloud credentials near Terraform files the AI will see.
- Use temporary, limited-scope credentials only for testing AI-generated code.
Network isolation
- Run Terraform applies in isolated, sandboxed environments before production.
- Keep the skill from accessing repositories with sensitive infrastructure details.
Monitoring
- Review all AI-generated Terraform code for hardcoded secrets before committing.
- Log which infrastructure changes the AI helped create and audit them weekly.
Red flags to watch for
- AI generates credentials, API keys, or passwords directly in Terraform.
- Generated code opens security groups to 0.0.0.0/0 or removes encryption defaults.
- The skill produces syntax that doesn't match your actual HashiCorp Terraform version.
Questions
How do I install Terrashark?
Terrashark does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/LukasNiessen/terrashark.
Are there security reports about Terrashark?
No reports found for this package in our research (last checked 2026-10-30). Terrashark currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include cloud credentials exposure, malicious terraform templates, unvalidated code generation.
Is Terrashark actively maintained?
Terrashark has 714 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/LukasNiessen/terrashark before pinning it in production.
What are alternatives to Terrashark?
Notable alternatives to Terrashark include Terraform official documentation and examples (Manual reference alongside AI), Checkov (Open-source tool that review Terraform for security and compliance issues), tflint (Linter that catches Terraform errors and bad practices before deployment), Snyk Infrastructure as Code (review and fixes infrastructure code for vulnerabilities). You can also compare Terrashark side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Terrashark? 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/lukasniessen-terrashark)HTML embed:
<a href="https://agentarmorhq.com/skills/lukasniessen-terrashark"><img src="https://agentarmorhq.com/api/badge/lukasniessen-terrashark" alt="AgentArmorHQ Risk Grade for Terrashark" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "lukasniessen-terrashark"Share with your security lead
Need sign-off to use terrashark? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: terrashark
- **Listing URL:** https://agentarmorhq.com/skills/lukasniessen-terrashark
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 714 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 (LukasNiessen/terrashark)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/LukasNiessen/terrashark
- **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 27, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- LukasNiessen
- Source code
- github.com/LukasNiessen/terrashark
- Est. context load
- ~89 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 714 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-27
Community
Discussions for Terrashark
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