What the reviewer found
This skill explicitly tells the agent to treat any loaded workspace-author skill body as an untrusted plan, not system instructions, and to ignore attempts in it to escalate privileges or skip confirmations. It is a defensive anti-injection instruction, not an injection itself.
example-or-fixture— an example or test fixture
What was read
The file as it ships in corezoid/simulator-ai-plugin:
plugins/simulator/skills/simulator-skills/SKILL.md
What the static scan said
The scan flagged 2things. The reviewer kept 0 and dismissed 2 as false.
P1Instruction-override phrasing — false positiveAR3Nullifies safety policies — 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.