What the reviewer found
A meta-skill for Claude to discover and self-install other skills, with an explicit trust boundary — untrusted 'live' skills require user confirmation, and fetched SKILL.md content is never auto-executed. The flagged `curl | bash` and `rm -rf ~/.claude/skills/<slug>` are documentation: one an anti-pattern to avoid, the other the user's own uninstall instructions for a directory this tool installed.
installs-software— installs software
What was read
The file as it ships in AGoldian/claudenv:
scaffold/global/.claude/skills/harness/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 1 and dismissed 2 as false.
SC2Downloads and executes remote code — 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.