The postinstall hook overwrites this package’s own AI-agent skill when it finds one already installed, without a separate user request. This automatic setup is limited in scope, so it warrants 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
Package installation runs the `postinstall` hook.
Impact
An installation can change instructions read by an installed AI agent without a separate user request; the observed change is limited to this package’s own skill.
Mechanism
The hook scans known agent skill locations and overwrites the generated `automations-cli/SKILL.md` file when that skill is already installed.
Evidence
package.jsonscripts/refresh-skills.mjsdist/chunk-UYRN5UJZ.js~/.claude/skills/automations-cli/SKILL.md~/.codex/skills/automations-cli/SKILL.md~/.copilot/skills/automations-cli/SKILL.md~/.cursor/skills/automations-cli/SKILL.md