Sinity/polylogue

github Rust re-analysis due unconfirmed MCP

A local evidence system for AI work—unifying ChatGPT, Claude, Codex, Gemini, and agent histories into one searchable, auditable archive.

maintainer: Sinity
licence: MIT
first seen: 2026-07-13
last seen: 2026-10-16
releases · 30d: 0
github stars: 10 reported
short id

risk

32/100 · heuristic grade

B low inferred analyzer v33 (current)

recent drift inferred + 20
tool safety inferred + 12

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.

risk trajectory

6 movements

7h ago B · 20 → B · 32
20h ago B · 17 → B · 20
1d ago D · 64 → B · 17
9w ago C · 52 → D · 64
12w ago D · 64 → C · 52
13w ago C · 56 → D · 64

vulnerabilities

0 CVEs

No known CVEs for this server.

tool safety

1 findings · grade factor +12

high dangerous code

committed secret: GitHub token

skills & danger signals

github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 8e61331 · analyzer v33 · 37m ago

skills & prompt files 1

agent-rules AGENTS.md

danger signals1

committed secret GitHub token crates/polylogue/src/mcp.rs :478 ghp_AA…(40 chars, redacted)

other grade factors

evidence elsewhere

recent drift +20 capability drift →

embed badge

readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:Sinity/polylogue/badge.svg)](https://mcpobservatory.com/servers/github:Sinity/polylogue/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 Sinity.