github Python analyzed cd4a4a0

willow-memory/willow-mcp

v2.33.0
github

Agent-neutral MCP server with persistent memory (SOIL + Postgres KB) and a sandboxed task queue. Manifest-based ACL; works with any stdio MCP client.

maintainer
willow-memory
licence
Apache-2.0
first seen
2026-08-21
last seen
2026-09-10
releases · 30d
73
short id
risk 65/100 · heuristic grade
D high inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • recent drift inferred + 20
  • tool safety inferred + 19
  • trust mitigators mixed − 9

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.

grade last moved 3d ago · see ecosystem CVEs →

risk trajectory 2 movements
  • D · 66 D · 65
  • C · 58 D · 66
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 3 findings · grade factor +19
  1. high dangerous code

    committed secret: private key · dynamic exec: __import__ sink

  2. medium toxic flow (lethal trifecta)

    lethal trifecta reachable across connected servers: this server can exfiltrate (network) while a connected dependency supplies private-data access / untrusted-content ingestion

  3. low exfiltration combo

    sensitive read and network capabilities split across this server's tools

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

analyzed commit cd4a4a0 · analyzer v33 · 3h ago

skills & prompt files 1

danger signals8

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:willow-memory/willow-mcp/badge.svg)](https://mcpobservatory.com/servers/github:willow-memory/willow-mcp/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 willow-memory.