szhygulin/vaultpilot-mcp
Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.
3 starsTypeScriptNOASSERTIONaaveai-agentarbitrumclaude
REVIEWED81/100
Scanned 2026-06-21 · deepseek v1
Dimension breakdown
Security
72/100
7 findings
Quality
85/100
No findings
License
75/100
No findings
Completeness
95/100
No findings
Findings (7)
MEDIUM: 4LOW: 2INFO: 1
- MEDIUMsecurityUnauthenticated feedback endpoint
- MEDIUMsecurityCustom call escape hatch bypasses dispatch allowlist
- MEDIUMsecurityRate-limited but unauthenticated issue filing
- MEDIUMsecuritySupply chain risk from patch-package and overrides
- LOWsecurityDemo mode allows real RPC reads
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 listingEmbed the badge.
Drop it into your README. Every view backlinks to this verification page.
Markdown
[](https://archimedes.market/r/szhygulin/vaultpilot-mcp)HTML
<a href="https://archimedes.market/r/szhygulin/vaultpilot-mcp"><img src="https://archimedes.market/api/badge/szhygulin/vaultpilot-mcp.svg" alt="Archimedes Trust Verified"/></a>