What the reviewer found
Near-duplicate of the aeon skill for a generic coding-agent runtime. Same as the Claude-specific copy: transcript mining is local and user-initiated, the MCP mention is a troubleshooting tip, and the `rm -rf` targets only a temporary git-mirror clone directory.
network— calls the vendor’s API
What was read
The file as it ships in aaronjmars/aeon-agent:
output/.tmp-aeon-update/head/plugin__skills__aeon__SKILL.md
What the static scan said
The scan flagged 4things. The reviewer kept 1 and dismissed 3 as false.
AS1Reads agent configuration directories — false positiveAS2Reads MCP configuration — false positiveRMRecursive force delete — false positiveNETMakes network calls — real
How this review was made
Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.