What the reviewer found
A defensive safety wrapper around the Gemini CLI: every flagged phrase (ignore previous instructions, reveal system prompt, act unrestricted, pipe ~/.ssh/id_rsa) is listed as something this skill BLOCKS, not something it does. It is a deny-rule table, not an injection.
What was read
The file as it ships in haoyuwang99/SafeSkill:
safeskillhub/safe-gemini/SKILL.md
What the static scan said
The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.
P1Instruction-override phrasing — false positiveP6Asks the agent to reveal its instructions — false positiveAR3Nullifies safety policies — false positivePE3Reaches for credential files — 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.