agentscope-ai/agentscope
Build and run agents you can see, understand and trust.
27,576 starsPythonApache-2.0agentchatbotlarge-language-modelsllm
SCANNED69/100
Scanned 2026-07-08 · deepseek v1
Dimension breakdown
Security
65/100
7 findings
Quality
85/100
No findings
License
95/100
No findings
Completeness
25/100
No findings
Findings (7)
HIGH: 2MEDIUM: 3LOW: 1INFO: 1
- HIGHsecurityPowerful tools exposed without input validation in example
- HIGHsecurityPotential command injection via Bash tool
- MEDIUMsecurityUnsafe deserialization risk via json_repair dependency
- MEDIUMsecurityPotential SSRF via model API calls
- MEDIUMsecurityPath traversal risk in file tools
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/agentscope-ai/agentscope)HTML
<a href="https://archimedes.market/r/agentscope-ai/agentscope"><img src="https://archimedes.market/api/badge/agentscope-ai/agentscope.svg" alt="Archimedes Trust Verified"/></a>