What the reviewer found
Admin CLI wrapper for a self-hosted Sub2API backend (pools upstream AI accounts behind proxies with TLS-fingerprint/anti-detection profiles) the user configures with their own base URL/API key; `accounts export` can dump credentials/tokens, which is the security-sensitive part -- dual-use admin tool, not malicious.
What was read
The file as it ships in Wei-Shaw/sub2api:
skills/sub2api-admin/SKILL.md
What the static scan said
The scan flagged 1thing. The reviewer kept 0 and dismissed 1 as false.
NETMakes network calls — false positive
How this review was made
Sonnet 5 read the files above on 6 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.