The runtime automatically configures a first-party, scoped Claude hook for eligible sessions, which merits a warning under the agent-integration policy. The inspected source does not establish a malicious attack or justify blocking publication.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
Starting a host-mode Claude session while the worktree guard is enabled, which is the default configuration.
Impact
The hook changes Claude session behavior by evaluating and potentially blocking tool actions outside the configured worktree boundaries.
Mechanism
The runtime writes guard settings under the session work directory and passes them to Claude. The settings run a command hook before matching tool use, with configured path boundaries.
Evidence
dist/session.cjsdist/worktree-guard.cjsdist/adapters/claude.cjsbin/worktree-guard-hook.cjs