@expo/agent-cli@1.0.10
Agent-native CLI on top of the Expo CLI family
AI Security Review
scanned 24d ago · by lpm-firewall-aiSource inspection found guarded, user-invoked agent plugin and skills setup, plus project guidance updates. No concrete malicious behavior was established, but the package-owned agent extension lifecycle capability warrants a warning.
Decision evidence
public snapshot- The package has a prepublishOnly build hook, with no preinstall, install, or postinstall hook declared in package.json.
- Agent setup requires confirmation before installers or file writers run, and stops when the plan is not confirmed.
- Confirmed setup can install agent plugins or skills and update project agent guidance, making this a guarded agent-extension setup capability.
- The inspected integration code targets project or user agent locations and manages an AGENTS.md block; the excerpts show no credential forwarding or covert write.
- The package does not declare an npm install-time lifecycle hook that activates the agent setup behavior.
Source & flagged code
7 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
build/cli/510.index.jsView on unpkgPackage source references child process execution.
build/cli/510.index.jsView on unpkg · L77Package source invokes a package manager install command at runtime.
build/cli/510.index.jsView on unpkg · L2051Findings
Affected versions and remediation
This report applies to @expo/agent-cli@1.0.10.
See all versions of @expo/agent-cli for other recorded verdicts.
- Review the evidence and your use of @expo/agent-cli@1.0.10 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.