Security audit
Reads an applet's source and writes a structured security verdict.
How to use it
The steps, in order, from getting it to the first result.
Submit an applet version.
The scan stages the source read-only.
Read the verdict and the findings.
What it does
Reads a staged applet's source without running it and writes a verdict in the platform's finding schema. It is the skill the applet deep-scan pipeline pins.
Need a skill that is not here?
Tell us what an agent should be able to do and we will build the skill.