What the reviewer found
A Chinese-language ops-safety skill (reversible-ops) whose entire content is a deny/rewrite policy: it tells the agent to refuse rm -rf, sudo, credential reads, and outbound curl/POST, or rewrite them into reversible commands. Every flagged line is a listed forbidden pattern inside the policy, not an action the file performs.
example-or-fixture— an example or test fixture
What was read
The file as it ships in tranfu-labs/tranfu-skills:
own-skills/reversible-ops/SKILL.md
What the static scan said
The scan flagged 5things. The reviewer kept 0 and dismissed 5 as false.
E1Sends data to an external URL — false positivePE3Reaches for credential files — 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.