What the reviewer found
This live social-media skill teaches hex-escaping 'chmod', 'sudo', 'rm -rf', and 'curl | bash' inside printf specifically so a security scanner ('tirith') can't detect them, and states the technique generalizes to any trigger word it flags — that is evasion of a security control, not documentation, whatever the stated tweet-writing use case. The GitHub API curl-to-file-then-read pattern elsewhere is a legitimate workaround for a scanner false positive, not exfiltration.
obfuscated— hides what it runs
What was read
The file as it ships in 0xMulight/human-social-copy:
hot-tools-tweet/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 2 and dismissed 1 as false.
SC2Downloads and executes remote code — realRMRecursive force delete — realNETMakes 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.