The automatic postinstall installs the package's own AI skill and, for Claude, adds a startup hook to the user's settings. The hook appears limited to the package's own project-orientation function, so this is a warning-level agent extension lifecycle risk rather than a control hijack.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; source fingerprint signature matched known malicious package; routed for review
Trigger
npm postinstall when a supported AI client is detected; the Claude hook is added when the skill is newly installed and Python is available.
Impact
The package is installed into the user's agent environment and its script runs at each Claude session start, where it can inject project orientation into the session.
Mechanism
Copies the package skill into the detected client's skill directory and writes a SessionStart command into Claude's settings.json to run the package's orientation script.
Evidence
package.jsonscripts/postinstall.jsscripts/lib.jsClient skill directory under the detected client homeClaude settings.json~/.agentic-sdlc/orient-hook-wired