AI tool security proxy: protect any AI tool server with customizable policies, path/command constraints, rate limiting, and audit logging. No code changes required.
LPM treats this as warn-only first-party agent extension lifecycle risk. A user-invoked global setup installs persistent hooks into Claude, Codex, and other AI-client configuration. Those hooks inspect tool activity, enforce remotely supplied policy, and transmit audit metadata.
Package source references child process execution.
dist/tui/index.jsView on unpkg · L143Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
dist/tui/index.jsView on unpkg · L13Source spawns a local helper that also contains network and dynamic execution context; review data flow before blocking.
dist/tui/index.jsView on unpkg · L13Source writes installer persistence such as shell profile or service configuration.
dist/tui/index.jsView on unpkg · L13Package source references dynamic require/import behavior.
dist/cli-launch.jsView on unpkg · L43A single source file combines environment access, network access, and code or shell execution; review context before blocking.
hooks/shield.mjsView on unpkg · L286Source file is highly similar to a previously finalized malicious package; route for source-aware review.
hooks/shield.mjsView on unpkgSource appears to send environment or credential material to an external endpoint.
hooks/guard.mjsView on unpkg · L13Source reaches cloud instance metadata or link-local credential endpoints.
hooks/guard.mjsView on unpkg · L13Manifest-reachable source overwrites another installed package with package-defined remote behavior.
dist/index.jsView on unpkgA manifest entrypoint or package-local install chain reaches persistence behavior.
dist/index.jsView on unpkg · L43Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
hooks/guard.bundled.mjsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
hooks/guard.bundled.mjsView on unpkgA manifest entrypoint or package-local install chain reaches credential exfiltration behavior.
dist/lib.jsView on unpkg · L42A manifest entrypoint or package-local install chain reaches a fixed external POST callback.
dist/lib.jsView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/index.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/lib.jsView on unpkgSource gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
dist/tui/index.jsView on unpkg · L13Source writes installer persistence such as shell profile or service configuration.
dist/tui/index.jsView on unpkg · L13Source spawns a local helper that also contains network and dynamic execution context; review data flow before blocking.
dist/tui/index.jsView on unpkg · L13Manifest-reachable source overwrites another installed package with package-defined remote behavior.
dist/index.jsView on unpkgA manifest entrypoint or package-local install chain reaches persistence behavior.
dist/index.jsView on unpkg · L43Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
hooks/guard.bundled.mjsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
hooks/guard.bundled.mjsView on unpkgA manifest entrypoint or package-local install chain reaches credential exfiltration behavior.
dist/lib.jsView on unpkg · L42A manifest entrypoint or package-local install chain reaches a fixed external POST callback.
dist/lib.jsView on unpkgPackage source references child process execution.
dist/tui/index.jsView on unpkg · L143Package source references dynamic require/import behavior.
dist/cli-launch.jsView on unpkg · L43A single source file combines environment access, network access, and code or shell execution; review context before blocking.
hooks/shield.mjsView on unpkg · L286Source file is highly similar to a previously finalized malicious package; route for source-aware review.
hooks/shield.mjsView on unpkgSource appears to send environment or credential material to an external endpoint.
hooks/guard.mjsView on unpkg · L13Source reaches cloud instance metadata or link-local credential endpoints.
hooks/guard.mjsView on unpkg · L13A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/index.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/lib.jsView on unpkg