github TypeScript analyzed 7e1c6ad

aeonfun/aeon

The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.

maintainer: aeonfun
licence: MIT
first seen: 2026-08-17
last seen: 2026-09-10
releases · 30d: 0
short id

risk 76/100 · heuristic grade

D high inferred analyzer v33 (current)

capability exposure inferred + 35
recent drift inferred + 20
tool safety inferred + 24
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 3 movements

3w ago D · 64 → D · 76
3w ago C · 56 → D · 64
3w ago C · 59 → C · 56

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 4 findings · grade factor +24

high dangerous code

committed secret: GitHub fine-grained PAT, OpenAI key · obfuscated payload: dynamic require()/import()
high hidden prompt content

2 file(s) with hidden prompt content: aeonfun-aeon-7e1c6ad/skills/heartbeat/SKILL.md (skill-exfil), aeonfun-aeon-7e1c6ad/skills/send-email/SKILL.md (skill-exfil): "secret→sink: - …
medium 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
medium 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 7e1c6ad · analyzer v33 · 6h ago

skills & prompt files 107

hidden: skill: skill-exfil aeonfun-aeon-7e1c6ad/skills/heartbeat/SKILL.md :285 secret→sink: - POST to `https://api.resend.com/emails`:
hidden: skill: skill-exfil aeonfun-aeon-7e1c6ad/skills/send-email/SKILL.md :88 secret→sink: 9. **Build payload + send.** Build the JSON with `python3` reading `RESEND_FROM`/`RESEND_REPLY_TO` from `os.environ` — so no secret-named var ever lands on a command line (a `--arg from "

danger signals8

suspicious endpoint api.telegram.org aeonfun-aeon-7e1c6ad/apps/dashboard/components/InstantModeCard.tsx :38 `curl "https://api.telegram.org/bot${botToken.trim() || '<YOUR_BOT_TOKEN>'}/setWebhook?url=${fullWorkerUrl || 'https://<your-worker>.workers.dev'}"`
suspicious endpoint t.me aeonfun-aeon-7e1c6ad/apps/dashboard/components/InstantModeCard.tsx :125 <a href="https://t.me/BotFather" target="_blank" rel="noopener noreferrer"
suspicious endpoint t.me aeonfun-aeon-7e1c6ad/apps/dashboard/components/SecretsPanel.tsx :164 href="https://t.me/BotFather"
suspicious endpoint api.telegram.org aeonfun-aeon-7e1c6ad/apps/dashboard/components/TelegramChatIdHelper.tsx :31 const getUpdatesUrl = trimmed ? `https://api.telegram.org/bot${trimmed}/getUpdates` : null
suspicious endpoint mcp.posthog.com (telemetry) aeonfun-aeon-7e1c6ad/apps/dashboard/lib/mcp-catalog.ts :109 url: 'https://mcp.posthog.com/mcp',
suspicious endpoint api.telegram.org aeonfun-aeon-7e1c6ad/apps/webhook/src/worker.js :228 await fetch(`https://api.telegram.org/bot${env.TELEGRAM_BOT_TOKEN}/answerCallbackQuery`, {
committed secret GitHub fine-grained PAT aeonfun-aeon-7e1c6ad/apps/dashboard/lib/github-auth.test.ts :13 github…(42 chars, redacted)
committed secret OpenAI key aeonfun-aeon-7e1c6ad/scripts/dry-run.sh :63 sk-DRY…(39 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:aeonfun/aeon/badge.svg)](https://mcpobservatory.com/servers/github:aeonfun/aeon/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 aeonfun.

aeonfun/aeon

skills & prompt files 107

danger signals8

Navigate

Stream

Features

Display