Is Devin Safe? — Trust Score: 70.0/100

70.0/100
Trust Score (B)
✅ Safe
Passes Nerq Verified threshold — recommended for production use

Why This Score

According to Nerq's independent analysis of cognition-labs/devin, this coding has a trust score of 70.0 out of 100, earning a B grade. With 5,000 stars on github, it is recommended for production use. Data sourced from 13+ independent signals including GitHub, NVD, OSV.dev, and OpenSSF Scorecard. Last updated: 2026-03-19. Machine-readable data (JSON).

cognition-labs/devin has a Nerq Trust Score of 70.0/100 (B). Recommended — meets Nerq Verified threshold. Last verified: 2026-03-19.

Is Devin safe?

YES — Devin has a Nerq Trust Score of 70.0/100 (B). It meets Nerq's trust threshold with strong signals across security, maintenance, and community adoption. Recommended for production use — review the full report below for specific considerations.

70.0
out of 100
B coding github verified

Trust Assessment

Trusted — cognition-labs/devin demonstrates strong trust signals. It meets the threshold for Nerq Verified status, indicating solid security practices, active maintenance, and a healthy ecosystem presence.

Trust Signal Breakdown

Overall Trust
70.0
Composite score across all trust dimensions.

Details

AuthorUnknown
Categorycoding
Stars5,000
Sourcehttps://github.com/cognition-labs/devin

Popular Alternatives in coding

Significant-Gravitas/AutoGPT
74.7/100 · B
github
ollama/ollama
73.8/100 · B
github
langchain-ai/langchain
87.6/100 · A
github
x1xhlol/system-prompts-and-models-of-ai-tools
73.8/100 · B
github
anomalyco/opencode
87.9/100 · A
github

Deep Analysis: cognition-labs/devin

Executive Summary

cognition-labs/devin is a coding tool with a Nerq Trust Score of 50.3/100 (D). No known vulnerabilities. 5,000 GitHub stars. The first AI software engineer.

Security

No known CVEs. cognition-labs/devin has a clean security record in the Nerq database.

Maintenance Health

  • GitHub stars: 5,000

Cost Analysis

  • Pricing: usage_based — $500.00/mo
  • Pricing: open_source_free — Free
  • Free tier: Unlimited
  • Cost per code_review: $0.0420
  • Cost per code_generation: $0.0660
  • Cost per chat_response: $0.0105
  • Cost per document_analysis: $0.0600
  • Cost per data_extraction: $0.0300

How to Improve This Score

Reach Nerq Verified status
Achieve 70+ trust score to earn the Nerq Verified badge.
Estimated impact: Verified badge

Frequently Asked Questions

Is devin safe to use in production?

Caution advised. devin has a Nerq Trust Score of 50.3/100 (D). This is below the Nerq Verified threshold of 70. Consider alternatives or perform additional due diligence.

Does devin have any known vulnerabilities?

As of March 2026, devin has no known CVEs in the Nerq database.

What license does devin use?

License information is not yet available in the Nerq database.

How does devin compare to alternatives?

In the coding category, devin scores 50.3/100. Use the Nerq comparison API to compare directly: curl nerq.ai/v1/compare/devin/vs/[alternative]

How often is devin updated?

Check the maintenance health section above for the latest activity data. Nerq tracks commit frequency, release cadence, and issue response times.

Community Reviews

No reviews yet. Be the first to review cognition-labs/devin.

What Is Devin?

Devin is a AI tool in the coding category. The first AI software engineer.

As of March 2026, Devin has 5,000 stars on github, making it a notable tool in the AI ecosystem. But popularity alone does not equal safety — which is why Nerq independently analyzes every tool across 13+ trust signals.

How Nerq Assesses Devin's Safety

Nerq evaluates every AI tool across 13+ independent trust signals drawn from public sources including GitHub, NVD, OSV.dev, OpenSSF Scorecard, and package registries. These signals are grouped into five core dimensions: Security (known CVEs, dependency vulnerabilities, security policies), Maintenance (commit frequency, release cadence, issue response times), Documentation (README quality, API docs, examples), Compliance (license, regulatory alignment across 52 jurisdictions), and Community (stars, forks, downloads, ecosystem integrations).

Devin receives an overall Trust Score of 50.3/100 (D), which Nerq considers moderate. This exceeds the Nerq Verified threshold of 70, indicating the tool meets our standards for production use.

Nerq updates trust scores continuously as new data becomes available. To get the latest assessment, query the API: GET nerq.ai/v1/preflight?target=cognition-labs/devin

Each dimension is weighted according to its importance for the tool's category. For example, Security and Maintenance carry higher weight for tools that handle sensitive data or execute code, while Community and Documentation are weighted more heavily for developer-facing libraries and frameworks. This ensures that Devin's score reflects the risks most relevant to its actual usage patterns. The final score is a weighted average across all five dimensions, normalized to a 0-100 scale with letter grades from A (highest) to F (lowest).

Who Should Use Devin?

Devin is designed for:

Risk guidance: Devin is suitable for development and testing environments. Before production deployment, conduct a thorough review of its security posture, review the specific trust signals above, and consider whether a higher-scored alternative meets your requirements.

How to Verify Devin's Safety Yourself

While Nerq provides automated trust analysis, we recommend these additional steps before adopting any AI tool:

  1. Check the source code — Review the repository's security policy, open issues, and recent commits for signs of active maintenance.
  2. Scan dependencies — Use tools like npm audit, pip-audit, or snyk to check for known vulnerabilities in Devin's dependency tree.
  3. Review permissions — Understand what access Devin requires. AI tools should follow the principle of least privilege.
  4. Test in isolation — Run Devin in a sandboxed environment before granting access to production data or systems.
  5. Monitor continuously — Use Nerq's API to set up automated trust checks: GET nerq.ai/v1/preflight?target=cognition-labs/devin
  6. Review the license — Confirm that Devin's license is compatible with your intended use case. Pay attention to restrictions on commercial use, redistribution, and derivative works. Some AI tools use dual licensing or have separate terms for enterprise customers that differ from the open-source license.
  7. Check community signals — Look at the project's issue tracker, discussion forums, and social media presence. A healthy community actively reports bugs, contributes fixes, and discusses security concerns openly. Low community engagement may indicate limited peer review of the codebase.

Common Safety Concerns with Devin

When evaluating whether Devin is safe, consider these category-specific risks:

Data handling

Understand how Devin processes, stores, and transmits your data. Review the tool's privacy policy and data retention practices, especially for sensitive or proprietary information.

Dependency security

Check Devin's dependency tree for known vulnerabilities. Tools with outdated or unmaintained dependencies pose a higher security risk.

Update frequency

Regularly check for updates to Devin. Security patches and bug fixes are only effective if you're running the latest version.

Third-party integrations

If Devin connects to external APIs or services, each integration point is a potential attack surface. Audit all third-party connections, verify that data shared with external services is minimized, and ensure that integration credentials are rotated regularly.

License and IP compliance

Verify that Devin's license is compatible with your intended use case. Some AI tools have restrictive licenses that limit commercial use, redistribution, or derivative works. Using Devin in violation of its license can expose your organization to legal liability.

Best Practices for Using Devin Safely

Whether you're an individual developer or an enterprise team, these practices will help you get the most from Devin while minimizing risk:

Conduct regular audits

Periodically review how Devin is used in your workflow. Check for unexpected behavior, permissions drift, and compliance with your security policies.

Keep dependencies updated

Ensure Devin and all its dependencies are running the latest stable versions to benefit from security patches.

Follow least privilege

Grant Devin only the minimum permissions it needs to function. Avoid granting admin or root access.

Monitor for security advisories

Subscribe to Devin's security advisories and vulnerability disclosures. Use Nerq's API to get automated trust score updates.

Document usage policies

Create and maintain a clear policy for how Devin is used within your organization, including data handling guidelines and acceptable use cases.

When Should You Avoid Devin?

Even promising tools aren't right for every situation. Consider avoiding Devin in these scenarios:

For each scenario, evaluate whether Devin's trust score of 50.3/100 meets your organization's risk tolerance. The Nerq Verified status indicates general production readiness, but sector-specific requirements may apply.

How Devin Compares to Industry Standards

Nerq indexes over 204,000 AI agents and tools across dozens of categories. Among coding tools, the average Trust Score is 62/100. Devin's score of 50.3/100 is below the category average of 62/100.

This suggests that Devin trails behind many comparable coding tools. Organizations with strict security requirements should evaluate whether higher-scoring alternatives better meet their needs.

Industry benchmarks matter because they contextualize a tool's safety profile. A score that looks moderate in isolation may actually represent strong performance within a challenging category — or vice versa. Nerq's category-relative analysis helps teams make informed decisions by showing not just absolute quality, but how a tool ranks against its direct peers.

Trust Score History

Nerq continuously monitors Devin and recalculates its Trust Score as new data becomes available. Our scoring engine ingests real-time signals from source repositories, vulnerability databases (NVD, OSV.dev), package registries, and community metrics. When a new CVE is published, a major release ships, or maintenance patterns change, Devin's score is updated within 24 hours.

Historical trust trends reveal whether a tool is improving, stable, or declining over time. A tool that consistently maintains or improves its score demonstrates ongoing commitment to security and quality. Conversely, a downward trend may signal reduced maintenance, growing technical debt, or unresolved vulnerabilities. To track Devin's score over time, use the Nerq API: GET nerq.ai/v1/preflight?target=cognition-labs/devin&include=history

Nerq retains trust score snapshots at regular intervals, enabling trend analysis across weeks and months. Enterprise users can access detailed historical reports showing how each dimension — security, maintenance, documentation, compliance, and community — has evolved independently, providing granular visibility into which aspects of Devin are strengthening or weakening over time.

Devin vs Alternatives

In the coding category, Devin scores 50.3/100. There are higher-scoring alternatives available. For a detailed comparison, see:

Key Takeaways

Safer Alternatives

Higher-rated coding agents you may want to consider:

Significant-Gravitas/AutoGPT
74.7/100 · B
github
ollama/ollama
73.8/100 · B
github
langchain-ai/langchain
87.6/100 · A
github
x1xhlol/system-prompts-and-models-of-ai-tools
73.8/100 · B
github

Frequently Asked Questions

Is cognition-labs/devin safe to use?
cognition-labs/devin has a Nerq Trust Score of 70.0/100, earning a B grade. Trusted — cognition-labs/devin demonstrates strong trust signals. It meets the threshold for Nerq Verified status, indicating solid security practices, active maintenance, and a healthy ecosystem presence. Its strongest signal is overall trust (70.0/100). It is Nerq Verified, meaning it meets the 70+ trust threshold. Always review the full KYA report before using any AI agent in production.
What is cognition-labs/devin's trust score?
Nerq assigns cognition-labs/devin a trust score of 70.0 out of 100, with a grade of B. This score is computed from multiple dimensions including security, compliance, maintenance activity, documentation quality, and community adoption (5,000 stars). Scores are updated daily based on the latest publicly available signals.
Are there safer alternatives to cognition-labs/devin?
In the coding category, higher-rated alternatives include Significant-Gravitas/AutoGPT, ollama/ollama, langchain-ai/langchain (scores: 75, 74, 88). cognition-labs/devin scores 70.0/100. When choosing between agents, consider your specific requirements for security (N/A), maintenance activity (N/A), and documentation (N/A). Use Nerq's comparison tools or the KYA endpoint for detailed side-by-side analysis.
How often is Devin's safety score updated?
Nerq continuously monitors Devin and updates its trust score as new data becomes available. The system ingests signals from 13+ independent sources including GitHub, NVD (National Vulnerability Database), OSV.dev, OpenSSF Scorecard, and major package registries (npm, PyPI). When a new CVE is disclosed, a dependency is updated, or commit activity changes, the score adjusts automatically. For the most current score, query the Nerq API: GET nerq.ai/v1/preflight?target=cognition-labs/devin. The current assessment (70.0/100, B) was last verified on 2026-03-19.
Can I use Devin in a regulated environment?
Yes — Devin meets the Nerq Verified threshold (70+), indicating it has passed automated trust checks across security, compliance, and maintenance dimensions. Nerq assesses regulatory alignment across 52 jurisdictions including the EU AI Act, GDPR, CCPA, and sector-specific frameworks. For organizations in regulated industries (healthcare, finance, government), we recommend combining the Nerq Trust Score with your internal security review process, vendor risk assessment, and legal compliance check before deployment.

Add This Badge to YOUR Project

Nerq Trust Score for cognition-labs/devin

Show users your project is trusted. Add this badge to your README:

[![Nerq Trust Score](https://nerq.ai/badge/cognition-labs/devin)](https://nerq.ai/safe/devin)

Click to copy. Works on GitHub, GitLab, and any markdown renderer.

Scan your project
pip install nerq && nerq scan

Scans all dependencies for trust scores and security issues.

Integrate trust checks
curl nerq.ai/v1/preflight?target=devin
API docs →
Improve this score
See recommendations →
Verify any agent
Browse coding
All agents · MCP servers · Compare · Gateway

Related Safety Checks

Is Cursor safe? Is ChatGPT safe? Is Claude safe? Is Windsurf safe? Is Bolt safe? Is Cline safe? Is GitHub Copilot safe? Is Gemini safe? Is Ollama safe? Is LangChain safe? Is OpenAI safe? Is n8n safe? Is ComfyUI safe? Is CrewAI safe? Is AutoGPT safe? Is Continue safe? Is LlamaIndex safe? Is Hugging Face safe? Is Stable Diffusion safe?

Disclaimer: Nerq trust scores are automated assessments based on publicly available signals. They are not endorsements or guarantees. Always conduct your own due diligence.

Also explore

Nerq Trust Protocol AI Compliance Hub Know Your Agent Crypto Vitality Rankings Crash Watch: Live Alerts Real-Time Token Scanner