AgentPod is building a private, secure device for your AI agent.The AgentPod device is coming.Coming soonBe first
We checked this and rejected itprivacy

Finance Assistant: why it is not safe to use

Finance Assistant mainly raised a privacy concern: by default, Claude Code may send financial conversation and file context to Anthropic.

What we found

Our review did not find hidden instructions, hardcoded secrets, obfuscated code, undisclosed remote code fetches, credential harvesting, or privilege escalation in the reviewed materials for Finance Assistant. The documented actions that could change the system, such as launch agent setup or data deletion, are described as requiring confirmation.

The main issue we found is privacy related. The repository says financial data is stored locally in `.finance` with no telemetry, but its security documentation also states that Claude Code sends conversation and file context to Anthropic by default unless the user switches to a local model. That means financial notes, budgeting details, or other money-related context may leave the device and be processed by a disclosed third party during normal use.

What to do instead

Use this skill only if you are comfortable with that default data flow. If you plan to work with sensitive financial information, switch to a local model before using the skill, and avoid including account-specific or highly sensitive details unless necessary. For lower-risk use, keep inputs limited to non-sensitive budgeting or planning data.

Want the same outcome, safely? Use our checked skill instead.

Source: https://github.com/googlarz/finance-assistant

We report what our security review found at the time we checked, with the goal of keeping people safe. Projects change; if a maintainer has since fixed this, we are glad to recheck it. Email hello@agentpod.com.

Copied to clipboard. Paste it into your AI (ChatGPT, Claude, or your agent) to add the skill.