What the reviewer found

This is Aeon's own auto-generated AGENTS.md (mirrors CLAUDE.md), documenting the framework's skill runner, secretcurl handling, and explicit anti-prompt-injection rules for fetched content. The flagged 'ignore previous instructions' text and .mcp.json mention are the framework's own defensive guidance, not an attack, and the HTML comment is a plain auto-gen notice.

• network — calls the vendor’s API

What was read

The file as it ships in aaronjmars/aeon-agent:

• 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