github JavaScript analyzed b740ea0

joergensentroels/Bureau

github

A hierarchy of AI agents that take real actions — shell, GitHub, email, purchases — behind an approval floor written in code, not configuration (Latch). Zero dependencies.

maintainer
joergensentroels
license
AGPL-3.0
first seen
2026-08-01
last seen
2026-08-01
releases · 30d
0
short id
risk 35/100 · heuristic grade
C elevated
  • capability exposure inferred + 35

inferred

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 4m ago · see ecosystem CVEs →

capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 13 findings · grade factor +0
  1. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  2. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  3. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  4. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  5. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  6. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/ev

  7. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/se

  8. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/se

  9. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/sp

  10. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/to

  11. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/to

  12. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/to

  13. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (joergensentroels-Bureau-b740ea0/to

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

analyzed commit b740ea0 · analyzer v28 · 3h ago

danger signals1

  • suspicious endpoint 169.254.169.254 (cloud metadata) joergensentroels-Bureau-b740ea0/test/net.test.mjs :26 chk(" JSON {url,method} to metadata IP → SSRF refused", /refused|private|internal/i.test((await apiCall('{"url":"http://169.254.169.254/","method":"delete"}')).error || ""));
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:joergensentroels/Bureau/badge.svg)](https://mcpobservatory.com/servers/github:joergensentroels/Bureau/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 joergensentroels.