Deep Security Scan

Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated independent repository-wide discovery passes with worker-specific threat models, semantically merge candidates, synthesize one canonical validation threat model, then run validation, attack-path analysis, and final reporting once. Repository-wide targets only; do not use for PRs, commits, branch diffs, working-tree diffs, or scoped paths.

cowork-os Updated 550 repo stars
A task in CoWork OS: the plan fills in, the agent asks before running a command, and the finished spreadsheet opens beside the chat

File contents

cowork-os/cowork-os commit 17a6a5edcf

Frequently asked questions

npx get-skill add cowork-os/deep-security-scan