Agent observability and knowledge capture layer for AI coding tools.
LPM treats this as warn-only first-party agent extension lifecycle risk. The postinstall hook can install this package’s generated onboarding skills into detected Claude or Codex user directories. This is a guarded first-party agent integration; no separate attack behavior was established.
Package defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgThe postinstall lifecycle automatically runs the Windows runtime setup and agent-skill setup scripts.
package.jsonView on unpkg · L108Package source references child process execution.
scripts/setup-agent-skills.mjsView on unpkg · L3This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
.output/cli.jsView on unpkgA single source file combines environment access, network access, and code or shell execution; review context before blocking.
.output/cli.jsView on unpkg · L65Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.
.output/cli.jsView on unpkg · L63A manifest entrypoint or package-local install chain reaches command-output exfiltration behavior.
.output/cli.jsView on unpkg · L63This report applies to @tonyclaw/agent-inspector@4.0.34.
See version security history for other recorded verdicts.
Evidence last updated: .
Package defines install-time lifecycle scripts.
package.jsonView on unpkg · L108Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg · L108The postinstall lifecycle automatically runs the Windows runtime setup and agent-skill setup scripts.
package.jsonView on unpkg · L108This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
.output/cli.jsView on unpkgA single source file combines environment access, network access, and code or shell execution; review context before blocking.
.output/cli.jsView on unpkg · L65Package source references child process execution.
scripts/setup-agent-skills.mjsView on unpkg · L3Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.
.output/cli.jsView on unpkg · L63A manifest entrypoint or package-local install chain reaches command-output exfiltration behavior.
.output/cli.jsView on unpkg · L63