What the reviewer found
Defense-in-depth guidance telling the agent to never read credential files (~/.aws, ~/.ssh, ~/.netrc, etc.) or run commands (curl|sh, npx) that untrusted tool output suggests. All three findings quote the file's own defensive rules against doing those things, not code that does them.
What was read
The file as it ships in tenet-security/agent-jackstop:
claude-code/skills/untrusted-tool-output/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.
PE3Reaches for credential files — false positiveSC2Downloads and executes remote code — false positiveNETMakes 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.