Run a FlareDeck agent on your own machine: it picks up cards assigned to it, works each one in a checkout of its own, and reports back on the card.
Allowed — no malicious behavior detected
19 low-signal patterns reviewed and cleared.
AI security review
scanned · by lpm-firewall-ai
The reviewed behaviors match a FlareDeck coding agent: remote commands are processed through the configured FlareDeck service, and Gemini requests use Google's API with the supplied key and prompt. Setup-related profile changes require an explicit setup command, and no malicious credential transfer or unrelated collection was identified.
Static reason
One or more suspicious static signals were detected.
Trigger
The user starts the agent or explicitly runs a feature that uses an external AI provider or remote command handling.
Impact
Expected agent operation: delegated work and command results are processed by FlareDeck, and prompts are sent to the selected AI service.
Mechanism
The agent sends feature data and credentials to the configured service endpoints; manager-issued commands are run locally and their output is sent back to FlareDeck.
Evidence
~/.tmux.confUser shell profile (only during explicit setup)
The package describes a FlareDeck agent that handles assigned cards.
Remote commands are claimed through the configured FlareDeck API using the agent's authentication, then their results are returned to that API.
Gemini requests send the supplied prompt and API key to Google's Gemini Developer API.
The setup command is invoked only when the user runs the explicit `setup` subcommand.
Evidence against
The launcher performs update checks during startup.
When running in tmux, the agent may modify the user's tmux configuration to enable scrollback.
Behavioral surface
SourceChild process · Crypto · Environment variables · Eval · Filesystem · Network · Shell · Web socket
Supply chainHigh entropy strings · URL strings
ManifestNo license
Scanned 130 files · 1.58 MB of source
14 external domains referenced
127.0.0.1
api.github.com
app.flaredeck.app
flaredeck-agent-861259873190.us-central1.run.app
generativelanguage.googleapis.com
github.com
jam.dev
mcp.cnjure.design
mcp.flaredeck.app
mcp.jam.dev
mcp.sceneflo.ai
openrouter.ai
pypi.org
registry.npmjs.org
Findings
6 high · 5 medium · 8 low
Automated scan signals; the review checked them and cleared this version. Where they are, most severe file first. Code opens a file's flagged lines, with their evidence, below.