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

trvl: why it is not safe to use

trvl was flagged for privacy review because it sends travel queries to third parties and can access local browser and credential stores for some providers.

What we found

Our review did not find hidden instructions, hardcoded secrets, destructive default behavior, or undisclosed remote code execution in the inspected repo materials. The main concern was data handling. The README says travel searches send query data to named third-party travel providers as part of normal operation. It also discloses a daily anonymous telemetry heartbeat, plus optional Google Calendar writes when that helper is used.

We also found local credential access that may be broader than some users expect. The README states the skill can automatically read browser cookies at startup for some providers, may trigger macOS Keychain access, can cache Booking.com tokens under `~/.trvl/cookies`, and for explicit AF-KLM use may read macOS Keychain or 1Password.

What to do instead

Use trvl only if you are comfortable with provider-side query sharing and the documented local credential access paths. Review and limit optional features such as telemetry and calendar integration before enabling them. Prefer running it in an environment with only the accounts and browser profiles you intend to use, and clear any cached tokens if you do not want them retained locally.

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

Source: https://github.com/MikkoParkkola/trvl

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.