github Python analyzed c6a4154 unconfirmed MCP

sunglasses-dev/sunglasses

github

Check outside content for prompt-injection patterns before your AI agent acts on it.

maintainer
sunglasses-dev
licence
MIT
first seen
2026-06-04
last seen
2026-09-10
releases · 30d
17
short id
risk 51/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • capability exposure inferred + 22
  • recent drift inferred + 20
  • 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 3d ago · see ecosystem CVEs →

risk trajectory 2 movements
  • C · 43 C · 51
  • A · 0 C · 43
capability exposure grade factor +22
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: AWS access key id, Anthropic key, GitHub token, OpenAI key, Slack token, Stripe live key

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

analyzed commit c6a4154 · analyzer v33 · 9m ago

skills & prompt files 13

danger signals16

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