mantis-critic

Assesses whether validated findings remain triggerable in production or release configurations.

Parent repository GitHub

Type: skill command
Repository: google/mantis
Readiness: Use only with expert supervision in isolated, restricted environments; not production-ready by its own documentation
Keywords: 5

Location

Repository path

mantis-critic/SKILL.md

Invocation

/mantis-critic [--target_root PATH] [--snapshot_root PATH] [--snapshot_id ID] [--state_root PATH]

Setup

Installation / activation

Stage 8 after validation; reads target code and threat-model context.

Keywords

criticproduction-viabilityrelease-buildtriagesnapshot

Repository context

google/mantis

Apache-2.0 portable Agent Skills and a Python/Google ADK reference harness for staged defensive security review, covering architecture and threat modeling through vulnerability research, deduplication, validation, sandboxed reproduction, exploit chaining, patch verification, calibration, reflection, reporting, and secure-development advice; Claude Code is not explicitly documented, so applicability is inferred for skill-compatible coding agents rather than established as a native Claude extension.

Application securitySecure code reviewThreat modelingVulnerability researchStatic analysisDynamic reproductionExploit analysisSecurity patchingDevSecOpsHardware and firmware securityInfrastructure as Code securitySecure software development

Open full repository research