What the reviewer found

This markitdown skill wraps Microsoft's markitdown-mcp converter with an explicit four-layer defense against path traversal and cloud-metadata SSRF, and its own 'security-lint: allow instruction-smuggling' comment marks the ignore-previous-instructions/rm -rf text as a teaching example of adversarial converted output. None of the flagged text is something the skill executes.

What was read

The file as it ships in event4u-app/agent-config:

• src/skills/markitdown/SKILL.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
• SSRF1Cloud metadata endpoint — false positive
• RMRecursive force delete — 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