What the reviewer found

This file is a prompt-injection defense: it instructs the agent to treat fetched content as untrusted and discard any embedded instructions, the opposite of what the rule fears. The HTML comment is a visible auto-generation header, and the remaining findings describe the project's own documented .mcp.json/WebFetch workflow.

What was read

The file as it ships in aeonfun/aeon:

• AGENTS.md

What the static scan said

The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.

• P1Instruction-override phrasing — false positive
• P2Hidden instructions — false positive
• AS2Reads MCP configuration — false positive
• NETMakes network calls — 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