The postinstall hook automatically replaces a named skill in global agent directories, which leaves a real extension lifecycle risk even though the skill is package-owned. The inspected runtime credential flow is consistent with user-directed file uploads, so the evidence supports a warning rather than a malware block.
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
Installing the package with its postinstall hook enabled.
Impact
An existing lj-awb skill can be overwritten, changing instructions available to future agent sessions.
Mechanism
install.mjs recursively removes each default lj-awb skill target and copies the bundled skill there, unless a skip variable is set.
Evidence
package.jsoninstall.mjsskills/lj-awb/SKILL.md~/.cc-switch/skills/lj-awb~/.codex/skills/lj-awb~/.claude/skills/lj-awb