Loading npm security reports…
A minimal CMD-style AI coding agent that works in the project where it is launched.
LPM treats this as warn-only first-party agent extension lifecycle risk. On npm installation, the package downloads and installs a provider executable outside the project. This creates a supply-chain risk because executable content is selected by a remotely fetched manifest.
Package defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
src/google-agent.jsView on unpkg · L83Package metadata claims a different repository identity while copied source loads a runtime dependency bridge.
src/google-agent.jsView on unpkg · L656A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
src/google-agent.js#virtual:normalized:round1View on unpkgThis report applies to antigyc@0.1.3.
See version security history for other recorded verdicts.
Evidence last updated: .
Package defines install-time lifecycle scripts.
package.jsonView on unpkg · L18Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg · L18A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
src/google-agent.js#virtual:normalized:round1View on unpkgSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
src/google-agent.jsView on unpkg · L83Package metadata claims a different repository identity while copied source loads a runtime dependency bridge.
src/google-agent.jsView on unpkg · L656