safety-review
CommandRun an AI safety review for a feature/model — harms, evaluations, guardrails, and a documented safety case.
@jassicsInstall CommandSecurity
Command
/intake
Intake and risk-tier an AI use case, then produce the governance/oversight record (NIST AI RMF / EU AI Act / ISO 42001).
> /plugin marketplace add jassics/awesome-claude-security
Command definition
intake.mddescription: Intake and risk-tier an AI use case, then produce the governance/oversight record (NIST AI RMF / EU AI Act / ISO 42001). argument-hint: [AI use case / system to register]
Run AI governance intake for: **$ARGUMENTS**
Walk it, using installed skills (note any whose plugin is missing):
1. **Intake** — `/responsible-ai-officer:ai-use-case-intake` to capture purpose, data, users, autonomy, and context. 2. **Risk-tier** — classify against the relevant regime (EU AI Act risk tiers / NIST AI RMF / ISO 42001) and decide the oversight level required. 3. **Assess** — `/ai-safety:responsible-ai-assessment` to evaluate the use case against responsible-AI principles and surface obligations. 4. **Document & oversee** — produce the governance record: risk tier, required controls/evals, accountable owner, and review cadence. Reference `/security-knowledge:framework-mapping` to align obligations to frameworks. 5. **Report** — `/security-reporting:executive-summary` for the approval record; route higher-risk cases to `/ai-safety-engineer:safety-review`.
For deep execution, hand off to the `responsible-ai-officer` agent. Tier first — the risk tier sets how much scrutiny everything downstream needs. No high-risk use case ships without an owner and a review date.
Ships withawesome-claude-security
A Claude Code plugin marketplace for the full cybersecurity & GenAI-security lifecycle — from recon and threat modeling to detection engineering, GRC, and CISO-level strategy. A pentester knows which OWASP test bends a broken-access-control endpoint.
11111 skills17 agents1 MCP
Stars on GitHub
Momentum
- stars in total
- 11
Other commands on awesome-claude-security.
@jassicsInstall Commanddefend
CommandRun a threat-informed defense cycle for a technique or threat — coverage check, hunt, detection, and purple-team validation.
@jassicsInstall Commandboard-brief
CommandBuild a board/executive security brief — strategy, quantified risk, and a board-ready deck.
@jassicsInstall Commandtech-review
CommandAssess technology/security risk for a strategic decision and frame the secure-by-design path.
@jassicsInstall Commandprecommit
CommandRun the pre-commit security gate on the current changeset and report a single pass/fail verdict.
@jassicsInstall Commandassessment
CommandRun a compliance gap-assessment for a framework, tie gaps to risk, and produce findings + remediation.
@jassicsInstall CommandMore commands from other plugins.
audit
CommandAudit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open…
@trailofbitsInstall Commandagt-check
CommandCheck text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
@microsoftInstall Commandarsenal
CommandShow which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from…
@awarexoneInstall Command