What the reviewer found
Tencent Yunding Lab skill-audit rubric (Chinese) that tells the agent how to grade another skill: every flagged item (curl -d, sudo, ~/.ssh and /etc/shadow, curl | bash, base64 -d | bash, rm -rf, eval/exec) is a row in its keyword tables or a listed attack phrase to refuse. It restricts itself to read-only tools and only uses web_fetch to read a remote script it is auditing.
network— calls the vendor’s API
What was read
The file as it ships in bighardperson/computer-science-skills-collection:
skills/Skill安全审计（云鼎实验室）/SKILL.md
What the static scan said
The scan flagged 8things. The reviewer kept 0 and dismissed 8 as false.
E1Sends data to an external URL — false positivePE2Asks for root — false positivePE3Reaches for credential files — false positiveSC2Downloads and executes remote code — false positiveSC3Encoded or obfuscated payload — false positiveRMRecursive force delete — false positiveNETMakes network calls — false positiveSHRuns shell commands — false positive
How this review was made
Fable 5.1 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.