github TypeScript analyzed 16b5ddf

scitex-ai/claude-code-telegrammer

Custom Telegram MCP server + TUI auto-responder for Claude Code — 10 MCP tools, SQLite message store, access control, reaction support

maintainer: scitex-ai
license: AGPL-3.0
first seen: 2026-07-10
last seen: 2026-07-18
releases · 30d: 10
short id

risk 57/100 · heuristic grade

C elevated

capability exposure inferred + 35
recent drift inferred + 20
tool safety inferred + 5
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.

graded 3m ago · see ecosystem CVEs →

risk trajectory 2 movements

2w ago C · 49 → C · 57
3w ago C · 52 → C · 49

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +5

medium dangerous code

dynamic exec: new Function()

skills & danger signals github-tarball

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

analyzed commit 16b5ddf · analyzer v28 · 3d ago

skills & prompt files 100

danger signals7

dynamic code execution new Function() scitex-ai-claude-code-telegrammer-16b5ddf/ts/dist/telegram-server.js :2893 const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/dist/telegram-server.js :13677 var API_BASE = `https://api.telegram.org/bot${TOKEN}`;
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/lib/config.ts :80 export const API_BASE = `https://api.telegram.org/bot${TOKEN}`;
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/lib/send-cli.ts :116 ` https://api.telegram.org/bot/sendMessage\n` +
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/lib/telegram-api.ts :115 const url = `https://api.telegram.org/file/bot${TOKEN}/${filePath}`;
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/test/config.test.ts :62 expect(API_BASE).toBe("https://api.telegram.org/botfake:token");
suspicious endpoint api.telegram.org scitex-ai-claude-code-telegrammer-16b5ddf/ts/test/health-checks.test.ts :264 const s = `Unable to connect. URL: https://api.telegram.org/bot${FAKE_TOKEN}/getWebhookInfo (${FAKE_TOKEN})`;

other grade factors evidence elsewhere

recent drift +20 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:scitex-ai/claude-code-telegrammer/badge.svg)](https://mcpobservatory.com/servers/github:scitex-ai/claude-code-telegrammer/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 scitex-ai.

scitex-ai/claude-code-telegrammer

skills & prompt files 100

danger signals7

Navigate

Stream

Features

Display