Skills/Glama/rootmind

rootmind@r1

CAUTION· install only

Publisher claims: "Search your own files from Claude & any MCP client: PDF, Office and more. Exact full-text search with page numbers, 100% local. Needs the RootMind app." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher cgaeking · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution 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 tauri.localhost, ngrok.com, claude.ai, githubusercontent.com — 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
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. 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 rootmind@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; README links to an external installer; README directs the reader to a committed installer. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsbackend/src/rootmind/config.py:330 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Environment-based settings (also read from a ``.env`` file in the working directory)."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
README links to an external installerREADME.md → https://github.com/cgaeking/rootmind/releases/latest/download/RootMind-Setup-x64.exehttps://github.com/cgaeking/rootmind/releases/latest/download/RootMind-Setup-x64.exeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
README directs the reader to a committed installerpackaging/winget/README.md:811. Download `RootMind-Setup-x64.exe` and `SHA256SUMS.txt` from the release and check the hashFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
README tells the reader to click past SmartScreenREADME.md:50"Windows protected your PC", choose **More info**, then **Run anyway** (theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
README directs the reader to a committed installerREADME.md:48**[RootMind-Setup-x64.exe](https://github.com/cgaeking/rootmind/releases/latest/download/RootMind-Setup-x64.exe)**.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsbackend/src/rootmind/config.py:680 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAPI keys from environment variables or a ``.env`` file are not mergedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/release_notes.py:98 · File permission modification command — agent changes file ownership/permissions| `{LINUX_APPIMAGE}` | The same as an AppImage for other distributions, without installation: `chmod +x {LINUX_APPIMAGE}`, then run it (needs FUSE 2, `libfuse2`). |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedbackend/src/rootmind/ocr.py:233 · Python subprocess execution detectedreturn subprocess.run( # noqa: S603 (a fixed program found above, no shell)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addressdesktop/src/i18n/labels.en.ts:71 · URL to a private-network address — a LAN or development targeturlPlaceholder: "http://192.168.1.10:8000",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Tunneling service URLdesktop/src/state/mcpClients.ts:8 · Tunneling service URL — may route traffic to attacker infrastructureexport const NGROK_DASHBOARD_URL = "https://dashboard.ngrok.com/";Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commandscripts/release_notes.py:97 · Privileged sudo command — agent may execute with elevated privileges| `{LINUX_RPM}` | The same for Fedora and openSUSE Tumbleweed: `sudo dnf install ./{LINUX_RPM}` (openSUSE: `sudo zypper install ./{LINUX_RPM}`). |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addressdesktop/src/i18n/labels.de.ts:71 · URL to a private-network address — a LAN or development targeturlPlaceholder: "http://192.168.1.10:8000",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsbackend/src/rootmind/config.py:332 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmodel_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationdesktop/src/i18n/labels.de.ts:147 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeautoUpdate: "Der RootMind-Dienst wird auf die Version dieser App aktualisiert …",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdesktop/src/i18n/labels.en.ts:147 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeautoUpdate: "Updating the RootMind service to this app's version …",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/prepare_backend.py:115 · Python subprocess execution detectedresult = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandscripts/release_notes.py:96 · Privileged sudo command — agent may execute with elevated privileges… approval, no Python. | | `{LINUX_DEB}` | The Linux app for Ubuntu and Debian: `sudo apt install ./{LINUX_DEB}`. On its first start it sets up its background service…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈33 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

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

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. README directs the reader to a committed installer≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  2. README tells the reader to click past SmartScreen≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Unclaimed publisher≈ +8 on the totalClaim cgaeking: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Tunneling service URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cgaekingPropose a patch to the maintainer