Skills/Glama/lppm-mcp

lppm-mcp@0.1.0

VERIFIED· not started

Publisher claims: "Enables AI assistants, HTTP clients, and Python programs to log in to Pradita University's research and community-service portal, list the menus available after login, read pages as text or tables, and monitor remaining Turnitin quota and submission history or submit new Turnitin check requests." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher alfa-yohannis · publishing for 0 daysInstalls 0Last detonated 2 h ago
$npx skills add lppm-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso google.com, lain.ac.id, pradita.ac.id — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathslppm_mcp/__init__.py:6 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesklien = KlienLppm() # kredensial dari .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/cli.py:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslppm-cek-login cek kredensial di setelan (.env) bisa dipakai loginFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_konfigurasi.py:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(induk / ".env").write_text("LPPM_USERNAME=induk\nLPPM_PASSWORD=induk\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/API.md:56 · Prompt injection — known jailbreak technique reference · informational: not an instruction filememakai `LPPM_USERNAME` dan `LPPM_PASSWORD` dari setelannya sendiri (`.env`).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/CLI.md:16 · Prompt injection — known jailbreak technique reference · informational: not an instruction file`lppm-petakan`, dan `lppm-turnitin` dengan argumen yang sama persis:Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstests/test_konfigurasi.py:74 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(akar_tiruan / ".env").write_text("LPPM_NAMA_INSTANSI=Dari ENV\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_konfigurasi.py:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(akar_tiruan / ".env").write_text("LPPM_NAMA_INSTANSI=Dari ENV\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/MCP.md:3 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileServer MCP membuka kemampuan yang sama dengan REST API dan CLI, sehingga asistenFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstests/conftest.py:388 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesKredensial asli di .env proyek tidak terbaca karena akar proyek dipindah keFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/conftest.py:386 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Setelan, .env, dan lppm.yaml mesin pengembang tidak boleh ikut menentukan hasil uji.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/CLI.md:17 · Prompt injection — known jailbreak technique reference · informational: not an instruction file`./lppm menu` dan `lppm-menu` setara.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/CLI.md:92 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileBentuk teks membuang menu, skrip, dan isian tersembunyi. Bentuk tabel menulisFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/lppm_client.py:140 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesLPPM_WEBSITE (alamat halaman login, seperti di .env.contoh) cukup untukFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/lppm_client.py:270 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(atur_setelan, environment, atau .env) saat login pertama. Membuat objekFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/MCP.md:130 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| `daftar_turnitin` | (tidak ada) | jatah dan riwayat cek Turnitin |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/mcp_server.py:79 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Cek apakah kredensial LPPM di setelan (.env) bisa dipakai login.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/API.md:120 · Prompt injection — known jailbreak technique reference · informational: not an instruction filedan `baris`. Tiap baris berkunci nama kolom, dan tautan di dalamnya dikumpulkanFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/konfigurasi.py:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files<akar>/.env kredensial (LPPM_USERNAME, LPPM_PASSWORD)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/conftest.py:412 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Kredensial karangan, diberikan lewat atur_setelan seperti dari .env."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/MCP.md:99 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileBerapa sisa jatah cek Turnitin saya, dan apa status pengajuan terakhir?Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/lppm_client.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# alamat bawaan; portal lain diatur lewat LPPM_WEBSITE/LPPM_BASE_URL di .env atauFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/mcp_server.py:59 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Kredensial diambil dari setelan server (.env); jangan meminta kata sandi "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_konfigurasi.py:126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(akar_tiruan / ".env").write_text("LPPM_USERNAME=0000000001\nLPPM_PASSWORD=sandi-karangan\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/konfigurasi.py:113 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Letak .env yang dipakai."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectiondocs/API.md:54 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileSetiap badan permintaan boleh membawa `username` (NIDN atau email) danFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/konfigurasi.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessebagai pustaka, site-packages jelas bukan tempat menaruh .env milikFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/mcp_server.py:81 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesSelalu login ulang dari awal, jadi berguna juga setelah .env diubah.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/konfigurasi.py:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Direktori tempat .env, lppm.yaml, dan data/ dicari."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/cli.py:151 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdescription="Cek kredensial LPPM di setelan (.env) bisa dipakai login."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_konfigurasi.py:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert konfigurasi.berkas_env() == aplikasi / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslppm_mcp/mcp_server.py:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(LPPM_USERNAME dan LPPM_PASSWORD di .env atau environment), jadi asisten tidakFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionREADME.md:9 · Prompt injection — known jailbreak technique reference · informational: not an instruction filepenelitian, PkM, dan unduh dokumen menyusul setelah halamannya dipetakan;Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:13 · Prompt injection — known jailbreak technique reference · informational: not an instruction file(data pengajaran) dan [sister-mcp](https://github.com/alfa-yohannis/sister-mcp)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/CLI.md:41 · Prompt injection — known jailbreak technique reference · informational: not an instruction file./lppm turnitin ... # jatah, riwayat, dan pengajuan cek TurnitinFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:7 · Prompt injection — known jailbreak technique reference · informational: not an instruction filesatu alat khusus: [cek Turnitin](#cek-turnitin), untuk memantau jatah danFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/API.md:60 · Prompt injection — known jailbreak technique reference · informational: not an instruction file`X-LPPM-Username` dan `X-LPPM-Password` dengan aturan yang sama: isi keduanyaFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/MCP.md:115 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileEmpat tool hanya membaca dan aman diizinkan otomatis: `cek_login`,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/API.md:64 · Prompt injection — known jailbreak technique reference · informational: not an instruction file(`umur_sesi_detik`). Login berjalan saat pertama dibutuhkan, dan diulang sendiriFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathslppm_mcp/konfigurasi.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesRahasia dipisah dari setelan dengan sengaja: `.env` memuat username/password danFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionREADME.md:14 · Prompt injection — known jailbreak technique reference · informational: not an instruction file(pengisian BKD). Ketiganya berdiri sendiri: kode, dokumentasi, contoh, danFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:6 · Prompt injection — known jailbreak technique reference · informational: not an instruction filesetelah login, dan pembaca halaman yang mengembalikan teks atau tabel), ditambahFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/CLI.md:48 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileKredensial selalu dibaca dari setelan (`.env`, environment) dan tidak pernahFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/MCP.md:116 · Prompt injection — known jailbreak technique reference · informational: not an instruction file`daftar_menu`, `ambil_halaman`, dan `daftar_turnitin`. Biarkan `ajukan_turnitin`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/prompt_mcp.md:30 · Prompt injection — known jailbreak technique reference · informational: not an instruction filedan sebutkan anggota serta skemanya.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/prompt_mcp.md:25 · Prompt injection — known jailbreak technique reference · informational: not an instruction filetahun, dan status tiap penelitian saya.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/prompt_mcp.md:5 · Prompt injection — known jailbreak technique reference · informational: not an instruction file`.env`; asisten tidak perlu dan tidak boleh menanyakan kata sandi.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/mcp_klien.json:11 · Prompt injection — known jailbreak technique reference · informational: not an instruction file"LPPM_AKAR_PROYEK menentukan di mana .env, lppm.yaml, dan data/ dicari;",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/prompt_mcp.md:20 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileBaca halaman profil LPPM (/infolppm/profil) dan ringkas tugas lembaganya.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/prompt_mcp.md:24 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileBuka menu penelitian di portal LPPM dan tampilkan tabelnya: judul, ketua,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionrequirements.txt:6 · Prompt injection — known jailbreak technique reference · informational: not an instruction file# pip install -e ".[semua]" + REST API, MCP, dan pytestFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/README.md:3 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileContoh siap jalan untuk ketiga mode. Semuanya butuh Python 3.10+ dan kredensialFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈35 tok
1 file · 32 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.