github Python analyzed fba3936

NuGuardAI/nuguard

github

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

maintainer
NuGuardAI
licence
NOASSERTION
first seen
2026-07-31
last seen
2026-09-10
releases · 30d
4
short id

NuGuardAI/nuguard is an MCP server distributed on github, maintained by NuGuardAI, tracked here since July 2026. It has shipped 15 releases and exposes 7 tools. Tools include nuguard_analyze, nuguard_behavior, nuguard_init, nuguard_policy_check, nuguard_redteam, nuguard_sbom_generate, and 1 more. Its composite risk grade is D — an inferred review prompt computed from observed signals, not a verdict.

what we found

Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.

Its 7 tools appear to reach filesystem, shell / exec, network, secrets and database, inferred from tool names, descriptions and input schemas rather than from observed behaviour.

full security breakdown →
tools 7
  • nuguard_analyze
  • nuguard_behavior
  • nuguard_init
  • nuguard_policy_check
  • nuguard_redteam
  • nuguard_sbom_generate
  • nuguard_scan
release cadence · 90d 6 releases
06-13 00:00 07-27 00:00 now
recent releases last 10
version date src
v0.9.4 2026-08-31 github
v0.9.3 2026-08-30 github
v0.9.2 2026-08-29 github
v0.9.1 2026-08-25 github
v0.8.8 2026-07-22 github
0.7.6 2026-06-19 github
0.5.5 2026-05-25 github
0.4.6 2026-05-17 github
0.4.4 2026-05-15 github
0.4.2 2026-05-09 github

view all →