What the reviewer found
Same spectra-ask assistant definition as the .cursor/commands copy: the flagged text is its own prompt-injection defense and credential/PII refusal rules, not an injection or a credential leak.
What was read
The file as it ships in gcake119/joplin-llm-wiki:
.cursor/skills/spectra-ask/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveAR2Strips warnings and disclaimers — 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.