MCP, MCP server
redmine_ai_helper
redmine_ai_helper, an MCP server listed in the PlugVet directory.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
NETWORK_HOST_FROM_INPUT INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL
Why this grade
- NETWORK_HOST_FROM_INPUT High
A file takes a URL or endpoint as input and has no fixed host list.
app/controllers/ai_helper_controller.rb, line 414
Rails.cache.fetch(cache_key, expires_in: 1.hour) do - INSTALL_REMOTE_SCRIPT Medium
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
.devcontainer/Dockerfile, line 15
RUN curl -LsSf https://astral.sh/uv/install.sh | sh - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
.claude/skills/commit/SKILL.md, line 35
- If anything looks like a secret or credential (`.env`, `*.pem`, `credentials.json`, API keys, etc.), unstage it and warn the user instead of committing it silently.
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.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
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
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
.devcontainer/Dockerfile, line 15
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
.devcontainer/Dockerfile, line 22
RUN curl -fsSL https://claude.ai/install.sh | bash
.devcontainer/Dockerfile, line 23
RUN curl -fsSL https://opencode.ai/install | bash
Show more
.devcontainer/Dockerfile, line 24
RUN curl https://qlty.sh | sh
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
app/controllers/ai_helper_controller.rb, line 414
Rails.cache.fetch(cache_key, expires_in: 1.hour) do
app/controllers/ai_helper_settings_controller.rb, line 125
setting.safe_attributes = params.fetch(:ai_helper_setting, {}).permit(*EMBEDDING_TEST_FIELDS)
assets/javascripts/autocompletion/ai_helper_assignment_suggestion.js, line 130
const response = await fetch(this.endpoint, {
Show more
assets/javascripts/autocompletion/ai_helper_auto_completion.js, line 409
fetch(this.options.endpoint, {
assets/javascripts/autocompletion/ai_helper_issue_autocompletion.js, line 90
const response = await fetch(config.duplicateCheckEndpoint, {
assets/javascripts/chat/ai_helper_command_completion.js, line 86
const response = await fetch(`${url}?${params}`);
assets/javascripts/project_health/ai_helper_health_report_editor.js, line 102
fetch(body.dataset.updateUrl, {
assets/javascripts/project_health/ai_helper_master_detail.js, line 137
return fetch(url, {
assets/javascripts/settings/ai_helper_chat_settings.js, line 144
fetch(url)
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL
.claude/skills/commit/SKILL.md, line 35
- If anything looks like a secret or credential (`.env`, `*.pem`, `credentials.json`, API keys, etc.), unstage it and warn the user instead of committing it silently.
.claude/skills/speckit-implement/SKILL.md, line 127
- **Node.js/JavaScript/TypeScript**: `node_modules/`, `dist/`, `build/`, `*.log`, `.env*`
.claude/skills/speckit-implement/SKILL.md, line 133
- **PHP**: `vendor/`, `*.log`, `*.cache`, `*.env`
Show more
.claude/skills/speckit-implement/SKILL.md, line 134
- **Rust**: `target/`, `debug/`, `release/`, `*.rs.bk`, `*.rlib`, `*.prof*`, `.idea/`, `*.log`, `.env*`
.claude/skills/speckit-implement/SKILL.md, line 135
- **Kotlin**: `build/`, `out/`, `.gradle/`, `.idea/`, `*.class`, `*.jar`, `*.iml`, `*.log`, `.env*`
.claude/skills/speckit-implement/SKILL.md, line 136
- **C++**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.so`, `*.a`, `*.exe`, `*.dll`, `.idea/`, `*.log`, `.env*`
.claude/skills/speckit-implement/SKILL.md, line 137
- **C**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.a`, `*.so`, `*.exe`, `*.dll`, `autom4te.cache/`, `config.status`, `config.log`, `.idea/`, `*.log`, `.env*`
.claude/skills/speckit-implement/SKILL.md, line 143
- **Docker**: `node_modules/`, `.git/`, `Dockerfile*`, `.dockerignore`, `*.log*`, `.env*`, `coverage/`
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
the file cap was reached before every file was read.
OBFUSCATION_FILE_CAP_REACHED
lib/redmine_ai_helper/assistant_provider.rb, line 1
# frozen_string_literal: true
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 1758e1681c1a. install fetches a script from the network. accepts a host from input, with no fixed list in this file. reads a credential or environment file. the file cap was reached before every file was read.
Date and source
Date checked:
github.com
Commit graded: 1758e1681c1aaaec86e0cd8e224ef4defa4e551d
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.