What the reviewer found

A read-only knowledge-base assistant's security instructions: every flagged line is the assistant defending itself against prompt injection (treat 'ignore previous instructions' in queries/documents as literal data) and refusing to output credentials or PII. These are the guardrails, not an attack.

What was read

The file as it ships in gcake119/joplin-llm-wiki:

• .cursor/commands/spectra-ask.md

What the static scan said

The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.

• P1Instruction-override phrasing — false positive
• P2Hidden instructions — false positive
• AR2Strips 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.

Produced by agentmods.dev · Sonnet 5 · 7 September 2026