github TypeScript analyzed 0f11d05

lolxl/safespace-mcp

github

The AI safety gateway for an agent's external surface — a provider-agnostic safety envelope (input sanitize + untrusted-content tagging, tier/scope/burst/recipient egress gates, autonomy hardening, run_id forensics, tokens behind a SecretBackend, full audit trail) between an AI agent and any source it touches. MIT.

maintainer
lolxl
licence
Apache-2.0
first seen
2026-06-11
last seen
2026-07-30
releases · 30d
0
short id
risk 44/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • 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.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 2 movements
  • B · 32 C · 44
  • A · 0 B · 32
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 2 findings · grade factor +12
  1. high dangerous code

    committed secret: Google OAuth client secret, Google API key, GitHub token, GitHub fine-grained PAT, Stripe live key, OpenAI key · obfuscated payload: dynamic require()/import()

  2. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

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

analyzed commit 0f11d05 · analyzer v33 · 2w ago

skills & prompt files 1

danger signals38

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:lolxl/safespace-mcp/badge.svg)](https://mcpobservatory.com/servers/github:lolxl/safespace-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 lolxl.