github Python analyzed 2984dfb unconfirmed MCP

273v/kaos-agents

github

Agentic runtime for KAOS: Runner, SessionMemory (with reflexion lessons), 5 patterns (Chat/PlanExecute/Research/Findings/Router), 14 MCP tools, FastAPI REST API, audit-trail telemetry recorder.

maintainer
273v
license
Apache-2.0
first seen
2026-06-22
last seen
2026-07-20
releases · 30d
0
short id
risk 49/100 · heuristic grade
C elevated
  • capability exposure inferred + 28
  • recent drift inferred + 12
  • tool safety inferred + 12
  • trust mitigators mixed − 3

inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 1m ago · see ecosystem CVEs →

risk trajectory 2 movements
  • B · 25 C · 49
  • A · 0 B · 25
capability exposure grade factor +28
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12
  1. high dangerous code

    committed secret: Anthropic key · dynamic exec: eval()/exec(), __import__()

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 2984dfb · analyzer v28 · 3h ago

skills & prompt files 2

danger signals5

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:273v/kaos-agents/badge.svg)](https://mcpobservatory.com/servers/github:273v/kaos-agents/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of 273v.