A real security audit means four different tools, four sets of output, and a person trying to reconcile them by hand. This squad runs all four at once and reports as one.
sonnet1 weekSemgrepOWASP ZAPCheckovTrivy
Claude
92ROI
78Scale
$4.6k92Saved
ROI for
README.md
Why this subagent
A real security audit means four different tools, four sets of output, and a person trying to reconcile them by hand. This squad runs all four at once and reports as one.
The lead agent fans out SAST, DAST, infrastructure, and supply-chain scans in parallel, then merges the results. You get a single ranked report with duplicates removed and reproduction notes, instead of four tabs of conflicting findings.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Each worker runs its scan in parallel: source analysis, live probing, infra config review, and dependency CVEs.
pending
Findings are deduplicated and scored by severity and exploitability across all four streams.
pending
The lead agent compiles one ranked report with reproduction notes and opens issues for the high-severity items.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
As the lead agent, run SAST, DAST, IaC, and supply-chain sub-agents in parallel, then merge their findings into a single deduplicated report ranked by severity with reproduction steps.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.