Skip to content
Baseline

$security-review

Review security, privacy, data-loss, trust, and authority risks.

Use for untrusted input, secrets, sensitive data, permissions, privileges, destructive actions, or external authority.

Intent-routed Independent skill Static instructions

BOUNDARY

What this skill owns

Technology-neutral security and authority risk

Input
The security-relevant design, code, CI workflow, or data flow
Output
Prioritized findings, mitigations, and residual risk
Stop condition
Material threats are addressed or waiting for explicit authority

INVOCATION

Ask for the activity, not the implementation detail.

Your agent may select this workflow when the intent matches. Use $security-review when you want to make the route deterministic.

Inspect the source

RELATED WORKFLOWS

$verify Review the governing input, complete diff, evidence, risks, and limitations. $ci-workflow Build or repair CI that produces traceable evidence with least privilege. $premortem Forecast plausible failure chains and make mitigations observable.