What the reviewer found
Claude Agent SDK reference doc. The flagged `system_prompt="Custom instructions"` is a code-comment describing an SDK constructor parameter, and "Block dangerous commands: rm -rf, sudo, etc." is a defensive best-practice bullet, not an executed command.
What was read
The file as it ships in btgaskin/claude-agent-sdk-skill:
skills/claude-agent-sdk/SKILL.md
What the static scan said
The scan flagged 2things. The reviewer kept 0 and dismissed 2 as false.
P1Instruction-override phrasing — false positiveRMRecursive 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.