What the reviewer found
copilot-instructions.md of engineering gotchas for this repo's own CI/tooling: the E2 finding is a rule to strip GIT_* env vars for test isolation (the opposite of harvesting), the rm -rf is documented git-worktree cleanup mechanics scoped to a worktree path, and the curl/PyPI check just compares a pinned security-scanner version.
What was read
The file as it ships in WhatIfWeDigDeeper/agent-skills:
.github/copilot-instructions.md
What the static scan said
The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.
E2Harvests environment variables — false positiveRMRecursive force delete — false positiveNETMakes network calls — false positiveSHRuns shell commands — 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.