github Rust analyzed 25773e2

fritzprix/libr-agent

Desktop AI agent with built-in tools. No complex setup, just productivity.

maintainer: fritzprix
license: MIT
first seen: 2026-06-06
last seen: 2026-08-02
releases · 30d: 43
short id

risk 15/100 · heuristic grade

B low

capability exposure inferred + 6
tool safety inferred + 12
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.

graded 1m ago · see ecosystem CVEs →

risk trajectory 2 movements

3w ago C · 44 → B · 15
5w ago A · 0 → C · 44

capability exposure grade factor +6

Inferred surface — each links to servers holding it:

network

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12

high dangerous code

suspicious bundled script in 3 file(s)

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 25773e2 · analyzer v28 · 18h ago

skills & prompt files 124

danger signals4

suspicious endpoint 175.115.246.118 fritzprix-libr-agent-25773e2/src/lib/ai-service/__tests__/desktop-fetch.test.ts :133 const response = await llmFetch('http://175.115.246.118:4444/v1/models', {
suspicious bundled script suspicious bundled script fritzprix-libr-agent-25773e2/.agents/skills/setup-wizard/scripts/install_uv.sh :23 if curl -LsSf https://astral.sh/uv/install.sh | sh; then
suspicious bundled script suspicious bundled script fritzprix-libr-agent-25773e2/.github/skills/setup-wizard/scripts/install_uv.sh :23 if curl -LsSf https://astral.sh/uv/install.sh | sh; then
suspicious bundled script suspicious bundled script fritzprix-libr-agent-25773e2/src-tauri/bundled_skills/setup-wizard/scripts/install_uv.sh :23 if curl -LsSf https://astral.sh/uv/install.sh | sh; then

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:fritzprix/libr-agent/badge.svg)](https://mcpobservatory.com/servers/github:fritzprix/libr-agent/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 fritzprix.

fritzprix/libr-agent

skills & prompt files 124

danger signals4

Navigate

Stream

Features

Display