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
20 low-signal patterns reviewed and cleared.
AI security review
scanned · by lpm-firewall-ai
The flagged command execution and persistence paths serve documented features: manager-requested remote commands and an explicit setup command that configures a user-owned npm prefix. The reviewed credentials and network requests are used with their corresponding services; no unrelated collection or unauthorized default action was found.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Remote execution requires a FlareDeck manager request; profile changes require invoking the explicit setup command.
Impact
A manager-authorized request can run commands as the agent's local user and return their output to FlareDeck.
Mechanism
The agent claims remote requests using its service token, runs the requested command with a time limit, and sends the result to FlareDeck. Service credentials are used for their corresponding service operations.
Evidence
User-selected shell profile during setup
Network endpoints2
FlareDeck host configured by the usergenerativelanguage.googleapis.com
Decision evidence
public snapshot
Evidence for AI clean decision
The package exposes `dist/cli.js` as its command-line entry point; its only lifecycle script is `prepublishOnly`.
Remote commands are a documented manager feature and are claimed from FlareDeck using the agent's token before execution.
The server handles remote-execution events, while the command output is returned to FlareDeck as the result.
Gemini requests send the supplied API key and prompt to Google's Gemini API for the package's stated briefing feature.
The setup command edits a shell profile only as part of the explicit `setup` command.
Evidence against
Remote commands execute manager-supplied shell commands on the agent machine and return their output to FlareDeck.
The package uses credentials for service requests and Git operations.
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
1 critical · 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.