Intercept security for Claude Code — deep AI security scans that supplement your scanners and write findings back to the Intercept platform. OAuth 2.1, no API key.
Command
Pull this repo's AI Advisors, verify each recommendation against your actual local code/tool state, and report a per-rec verdict (already-mitigated / valid / overstated-FP / partially-done) with local evidence. Read-only.
Command
Fix a specific Intercept finding end-to-end — verify, apply the fix, prove it, mark it resolved.
Command
Natural-language security hunt across the repo (auth bypass, tenant isolation, SSRF, insecure deserialization, business-logic), recorded in Intercept. Secrets are out of scope (the static scanner's lane).
Command
Show this repo's Intercept security posture — score, grade, finding breakdown, and what's driving it.
Command
Deep AI security scan of this repo — supplements your scanners by targeting image contents, cloud/infra posture, and cross-file logic, then records new findings in Intercept.
Command
Pull open Intercept findings, verify each against the code, and clear false positives / confirm real ones.