bmdhodl/agent47
Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.
3 starsPythonMITai-agentsai-safetyanthropicdeveloper-tools
VERIFIED90/100
Scanned 2026-06-22 · deepseek v1
Dimension breakdown
Security
85/100
4 findings
Quality
88/100
No findings
License
95/100
No findings
Completeness
95/100
No findings
Findings (4)
MEDIUM: 2LOW: 1INFO: 1
- MEDIUMsecurityPotential data exfiltration via HttpSink
- MEDIUMsecurityNo input validation on trace event data
- LOWsecuritySecrets in configuration file warning not enforced
- INFOsecurityMCP server not reviewed
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/bmdhodl/agent47)HTML
<a href="https://archimedes.market/r/bmdhodl/agent47"><img src="https://archimedes.market/api/badge/bmdhodl/agent47.svg" alt="Archimedes Trust Verified"/></a>