The postinstall hook automatically overwrites pre-existing AI-agent skill files outside the package directory. Because the changes are limited to this CLI's own skill and skip agents without it, this is an agent extension lifecycle risk warranting a warning rather than a malicious verdict.
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 install runs the package's postinstall hook.
Impact
Agent instructions are changed without an explicit skill-update command; this is an install-time change limited to the package's own skill.
Mechanism
The hook checks supported agent skill locations and replaces any existing automations-cli/SKILL.md with generated content.
Evidence
package.jsonscripts/refresh-skills.mjsdist/chunk-LT3WXWBX.js$HOME/.claude/skills/automations-cli/SKILL.md$HOME/.codex/skills/automations-cli/SKILL.md$HOME/.copilot/skills/automations-cli/SKILL.md$HOME/.cursor/skills/automations-cli/SKILL.md$HOME/.gemini/config/skills/automations-cli/SKILL.md