MCP, MCP server
Smart Study Agent
The AI study agent that learns how you learn — a reinforcement-learning policy decides what you study next, an FSRS memory model decides when you review it, and an LLM generates the quizzes in between.
Compatibility: Not stated.
Grade C
One Medium finding. Read the report before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
OBFUSCATION_ENCODED_BLOB
Why this grade
- OBFUSCATION_ENCODED_BLOB Medium
Contains a long base64 shaped string in a file that should be readable.
chrome-extension/lib/pdfjs/pdf.mjs, line 1
/**
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Pass
No shell or command execution found, and no extra permission was declared.
Install and update
Concern
dependencies are not pinned.
INSTALL_UNPINNED
requirements.txt, line 1
anthropic>=0.40.0
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
chrome-extension/lib/extractors.js, line 73
const resp = await fetch(meta.trackUrl);
chrome-extension/lib/llm_backends.js, line 8
const resp = await fetch("https://api.anthropic.com/v1/messages", {
chrome-extension/lib/llm_backends.js, line 47
const resp = await fetch("https://router.huggingface.co/v1/chat/completions", {
Show more
chrome-extension/lib/pdf_extract.js, line 16
const resp = await fetch(url, { cache: "no-store" });
chrome-extension/lib/pdfjs/pdf.mjs, line 21
*/var t={d:(e,i)=>{for(var s in i)t.o(i,s)&&!t.o(e,s)&&Object.defineProperty(e,s,{enumerable:!0,get:i[s]})},o:(t,e)=>Object.prototype.hasOwnProperty.call(t,e)},__webpack_exports__
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
app.py, line 353
"use_mock": not (os.environ.get("ANTHROPIC_API_KEY")
app.py, line 355
or os.environ.get("HF_TOKEN")),
app.py, line 357
"Claude API" if os.environ.get("ANTHROPIC_API_KEY")
Show more
app.py, line 360
else "HF Inference (Kimi-K2)" if os.environ.get("HF_TOKEN")
demo_auto.py, line 76
use_mock = not os.environ.get("ANTHROPIC_API_KEY")
hf_client.py, line 91
api_key=api_key or os.environ.get("HF_TOKEN"),
hf_client.py, line 112
api_key=os.environ.get("SMARTSTUDY_LLM_API_KEY"),
smartstudy_agent.py, line 185
elif api_key or os.environ.get("ANTHROPIC_API_KEY"):
.env.example, line 1
# Copy this file to .env and fill in your real values.
.env.example, line 2
# .env is gitignored - your keys will NOT be committed.
.gitignore, line 1
# API keys & secrets
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Concern
contains an encoded blob in a file that should be readable.
OBFUSCATION_ENCODED_BLOB
chrome-extension/lib/pdfjs/pdf.mjs, line 1
/**
chrome-extension/lib/pdfjs/pdf.worker.mjs, line 1
/**
chrome-extension/lib/pdfjs/pdf.mjs, line 21
*/var t={d:(e,i)=>{for(var s in i)t.o(i,s)&&!t.o(e,s)&&Object.defineProperty(e,s,{enumerable:!0,get:i[s]})},o:(t,e)=>Object.prototype.hasOwnProperty.call(t,e)},__webpack_exports__
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 1f0ab5c160f1. dependencies are not pinned. can reach a host that is not written as a fixed address. reads a credential or environment file. contains an encoded blob in a file that should be readable.
Date and source
Date checked:
github.com
Commit graded: 1f0ab5c160f1aedfb25d6ecd7fa77fc53c8bcc78
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.