Trust Engine/MCP Server

hidai25/eval-view

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

117 starsPythonApache-2.0agent-benchmarkagent-evaluationai-agentscrewai
REVIEWED79/100

Scanned 2026-06-19 · deepseek v1

Dimension breakdown

Security

85/100

5 findings

Quality

85/100

No findings

License

95/100

No findings

Completeness

45/100

No findings

Findings (5)

MEDIUM: 2LOW: 2INFO: 1
  • MEDIUMsecurityAPI key handling relies on environment variables without validation
  • MEDIUMsecurityOptional telemetry dependency may collect usage data
  • LOWsecurityMypy type checking disabled on multiple modules
  • LOWsecurityUse of eval or exec not visible but could be present in unexamined code
  • INFOsecurityLicense is Apache-2.0, which is permissive

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Trust badge — flat styleTrust badge — for-the-badge style

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/hidai25/eval-view.svg)](https://archimedes.market/r/hidai25/eval-view)

HTML

<a href="https://archimedes.market/r/hidai25/eval-view"><img src="https://archimedes.market/api/badge/hidai25/eval-view.svg" alt="Archimedes Trust Verified"/></a>
hidai25/eval-view — Archimedes Trust | Archimedes