First public release
- Scanning:
scan,scan-all,diff,watchandgatecommands, with text, JSON and SARIF 2.1.0 output. - Detection: deterministic L1 analysis for all 11 threat classes, using pattern, Unicode, entropy and taint engines plus a capability differ for privilege escalation.
- Integrations: an MCP server (build with
--features mcp) and the opt-in L3 behavioral sandbox. - Reproducible output:
--deterministicgives byte-identical results, and--offlineis on by default. - Exit codes:
0clean,1error,2findings,3coverage below threshold.
- Everything sent to a model first passes through
skill-doctor-neutralize(SD-11 protection). - Higher layers can only add findings. They never remove, downgrade or reclassify L1 findings.
- Findings, reports and logs show secret names, never secret values.

