What the reviewer found
The SKILL.md behind the hl-permission command: a Python script that appends the same four broad Edit/Write/Bash/Read allow-rules to the project's settings.local.json. Curl|bash, sudo, dd, and rm -rf are risks the file's own warning calls out, including prompt-injection risk, not actions the script performs.
settings-edit— edits agent settings
What was read
The file as it ships in aizhangdeshuai-cmd/hlskills:
hl-permission/SKILL.md
What the static scan said
The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.
SC2Downloads and executes remote code — false positiveAS1Reads agent configuration directories — false positiveRMRecursive force delete — false positiveNETMakes network calls — false positive
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.