What the reviewer found
A defensive 'safe' wrapper: every flagged string (rm -rf, curl|bash, override phrasing) sits inside a BLOCK rule the skill refuses to run. It is a guardrail, not an attack.
What was read
The file as it ships in haoyuwang99/SafeSkill:
safeskillhub/safe-safe/SKILL.md
What the static scan said
The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.
P1Instruction-override phrasing — false positiveSC2Downloads and executes remote code — false positiveRMRecursive force delete — false positiveNETMakes network calls — false positive
How this review was made
opus-4-8 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.