This is a first-party, user-command-triggered AI-agent extension setup with behavior-bearing hooks, so it warrants a warning under the stated policy. No concrete malicious chain or unconsented install-time control-surface mutation was found.
Static reason
One or more suspicious static signals were detected.
Trigger
Running `eai init` without `--no-gofer`, then using the configured Claude project.
Impact
Project Claude sessions execute bundled hooks and receive locally persisted context.
Mechanism
Project-local Claude hook installation and memory-context injection.
Evidence
package.jsondist/commands/init.jsdist/lib/gofer-installer.jsresources/gofer/hook-scripts/user-prompt-submit.mjsresources/gofer/hook-scripts/post-tool-use.mjsresources/gofer/hook-scripts/agent-stop.mjs.claude/settings.json.specify/scripts/hooks/user-prompt-submit.mjs.specify/scripts/hooks/post-tool-use.mjs.specify/scripts/hooks/agent-stop.mjs