Fellowship Code安全吗？

Fellowship Code安全吗？

信任评分详情 — Fellowship Code has a Nerq Trust Score of 65.8/100 (C). Measured across 5 independent trust signals.

What Is Fellowship Code?

Fellowship Code is a software tool in the coding category: An open-source multi-agent AI engineering team for Cursor and Claude Code.. Nerq Trust Score: 66/100 (C).

Nerq independently analyzes every software tool, app, and extension across multiple trust signals including 安全性 vulnerabilities, 维护 activity, license 合规性, and 社区采用.

How Nerq Assesses Fellowship Code's Safety

Nerq's Trust Score is calculated from 13+ independent signals aggregated into five 维度. Here is how Fellowship Code performs in each:

• 安全性 (0/100): Fellowship Code's 安全性 posture is poor. This score factors in known CVEs, dependency vulnerabilities, 安全性 policy presence, and code signing practices.
• 维护 (1/100): Fellowship Code is potentially abandoned. We track commit frequency, release cadence, issue response times, and PR merge rates.
• Documentation (1/100): Documentation quality is insufficient. This includes README completeness, API 文档, usage examples, and contribution guidelines.
• Compliance (100/100): Fellowship Code is broadly compliant. Assessed against regulations in 52 司法管辖区s including the EU AI Act, CCPA, and GDPR.
• Community (0/100): Community adoption is limited. 基于 GitHub stars, forks, download counts, and ecosystem integrations.

The overall Trust Score of 65.8/100 (C) is the weighted combination of these measured signals. It is a measurement, not a pass/fail or suitability judgment — weigh the individual signals against your own requirements.

Who Typically Evaluates Fellowship Code?

Fellowship Code is commonly evaluated by:

• Developers and teams working with coding tools
• Organizations evaluating AI tools for their stack
• Researchers exploring AI capabilities in this domain

How to read the signals: Fellowship Code's measured signals (安全性 0/100, 维护 1/100, 文档 1/100, community 0/100) are shown above. These are measurements, not a suitability judgment — weigh each signal against the requirements of your own use case and risk tolerance.

How to Verify Fellowship Code's Safety Yourself

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

1. Check the source code — 查看 repository's 安全性 policy, open issues, and recent commits for signs of active 维护.
2. Scan dependencies — Use tools like npm audit, pip-audit, or snyk to check for known vulnerabilities in Fellowship Code's dependency tree.
3. 评论 permissions — Understand what access Fellowship Code requires. Software tools should follow the principle of least privilege.
4. Test in isolation — Run Fellowship Code 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=fellowship-code
6. 查看 license — Confirm that Fellowship Code'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 安全性 concerns openly. Low community engagement may indicate limited peer review of the codebase.

Common Safety Concerns with Fellowship Code

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

Fellowship Code and the EU AI Act

Fellowship Code is classified as Minimal Risk under the EU AI Act. This is the lowest risk category, meaning it faces minimal regulatory requirements. However, transparency obligations still apply.

Nerq's 合规性 assessment covers 52 司法管辖区s worldwide. For organizations deploying AI tools in regulated environments, understanding these classifications is essential for legal 合规性.

Best Practices for Using Fellowship Code Safely

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

Situations That Warrant 独立 Review of Fellowship Code

Nerq's signals are one input. In the following situations, evaluate Fellowship Code's measured signals against your own requirements before making a decision:

• Environments handling sensitive or regulated data (healthcare, finance, government)
• Mission-critical systems where downtime has significant business impact
• Deployments with strict regulatory requirements that must be independently validated

For each situation, compare Fellowship Code's measured trust score of 65.8/100 and its individual signals against your organization's own criteria. Nerq does not assert whether Fellowship Code is suitable for any particular use.

How Fellowship Code Compares to Industry Standards

Nerq indexes over 6 million software tools, apps, and packages across dozens of categories. Among coding tools, the average Trust Score is 62/100. Fellowship Code's score of 65.8/100 is above the category average of 62/100.

This positions Fellowship Code favorably among coding tools. While it outperforms the average, there is still room for improvement in certain trust 维度.

Industry benchmarks matter because they contextualize a tool's safety profile. A score that looks 中等 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 Fellowship Code 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 维护 patterns change, Fellowship Code'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 安全性 and quality. Conversely, a downward trend may signal reduced 维护, growing technical debt, or unresolved vulnerabilities. To track Fellowship Code's score over time, use the Nerq API: GET nerq.ai/v1/preflight?target=fellowship-code&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 — 安全性, 维护, 文档, 合规性, and community — has evolved independently, providing granular visibility into which aspects of Fellowship Code are strengthening or weakening over time.

Fellowship Code vs 替代品

In the coding category, Fellowship Code scores 65.8/100. There are higher-scoring alternatives available. For a detailed comparison, see:

• Fellowship Code vs AutoGPT — Trust Score: 65.3/100
• Fellowship Code vs ollama — Trust Score: 64.4/100
• Fellowship Code vs langchain — Trust Score: 77.0/100

主要结论

• Fellowship Code has a measured Nerq Trust Score of 65.8/100 (C) — a composite of independent signals, not a suitability judgment.
• Among coding tools, Fellowship Code scores above the category average of 62/100 (a positional measurement relative to peers).
• The individual signals — 安全性, 维护, 文档, 合规性, community — are shown above. Weigh them against your own requirements.
• Query the current measured values via Nerq's Preflight API.