npm JavaScript analyzed 2.1.2

agentic-flow

v2.1.2
npm

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

maintainer
ruvnet
license
MIT
first seen
2026-05-22
last seen
2026-08-14
releases · 30d
2
short id
risk 38/100 · heuristic grade
C elevated
  • capability exposure inferred + 35
  • tool safety inferred + 5
  • supply-chain attested + 6
  • trust mitigators mixed − 8

attested 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 9m ago · see ecosystem CVEs →

risk trajectory 5 movements
  • D · 61 C · 38
  • D · 68 D · 61
  • C · 59 D · 68
  • C · 54 C · 59
  • C · 59 C · 54
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +5
  1. medium dangerous code

    dynamic exec: new Function()

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

analyzed v2.1.2 · analyzer v32 · 14h ago

skills & prompt files 200

danger signals1

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:agentic-flow/badge.svg)](https://mcpobservatory.com/servers/npm:agentic-flow/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 ruvnet.