jassics

jassics/awesome-claude-security

Plugin Claude Code

Plugin marketplace listing 45 plugins: security-diagramming, security-reporting, security-integrations, security-knowledge, threat-modeling.

jassics/awesome-claude-security

Instructions file

Claude Code instructions for jassics/awesome-claude-security, covering claude.md, what this repo is, architecture, conventions (consistency matters across plugins) and common commands.

jassics/awesome-claude-security

Plugin Claude Code

Security for autonomous, tool-using AI agents: review, tool-permission audit, autonomy-boundary testing for excessive agency, MCP server trust review, agent harness/runtime testing, and agent-to-agent (A2A) protocol trust.

jassics/awesome-claude-security

Skill Claude CodeCodex

Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain privilege narrowing. Use when an orchestrator dispatches to sub-agents or peer agents (same or different trust domain) rather than calling a tool — distinct…

jassics/awesome-claude-security

Skill Claude CodeCodex

Test the agent execution harness/runtime itself — LangChain/LangGraph, AutoGen, CrewAI, custom ReAct-style loops, or computer-use/browser-use agents — for intermediate-state poisoning, unscoped action spaces, and missing resource limits. Use when the agent isn't built on Claude Code (see claude-config-security for…

jassics/awesome-claude-security

Skill Claude CodeCodex

Assess an autonomous / tool-using AI agent for security end-to-end: tool privileges, autonomy and approval boundaries, excessive agency, memory/state poisoning, and multi-agent trust. Use when reviewing the security of an AI agent or agentic workflow.

jassics/awesome-claude-security

Skill Claude CodeCodex

Test what an AI agent will actually do without human confirmation, including under injected-goal / prompt-injection scenarios, to validate its autonomy and approval boundaries. Use on an authorized agent to confirm excessive-agency controls hold in practice.

jassics/awesome-claude-security

Skill Claude CodeCodex

Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description and result poisoning, confused-deputy risk, consent/scope UX, and supply-chain pinning. Use when an agent or assistant integrates one or more MCP servers, especially third-party or community…

jassics/awesome-claude-security

Skill Claude CodeCodex

Inventory the tools/functions an AI agent can call and audit their privileges, side effects, and approval requirements to find excessive-agency and least-privilege gaps. Use when reviewing an agent's tool/function surface.

jassics/awesome-claude-security

Plugin Claude Code

AI safety engineer role bundle: build and operationalize safeguards (evals-in-CI, guardrails, monitoring, safety cases, RAI governance). Auto-installs the ai-safety stack.

jassics/awesome-claude-security

Agent

Builds and operationalizes AI safety — turning safety assessments into shipped safeguards: safety evals in CI/CD, guardrail integration, monitoring and drift detection, AI-incident response, safety cases, and responsible-AI governance. Use to design or stand up the safety machinery around an AI system, not just assess…

jassics/awesome-claude-security

Command

Run an AI safety review for a feature/model — harms, evaluations, guardrails, and a documented safety case.

jassics/awesome-claude-security

Skill Claude CodeCodex

Operationalize a safety/prompt-injection eval suite into an enforced CI gate — not just a one-off report — using the ready-to-copy promptfoo/garak template, a regression baseline, and a burn-in rollout. Use when a safety eval already exists (or is being designed) and needs to actually block regressions on every…

jassics/awesome-claude-security

Skill Claude CodeCodex

Assemble a structured assurance / safety case for deploying an AI system — an explicit argument that it is acceptably safe for its context, backed by evidence (harm model, evals, guardrails, fairness, governance). Use to support a go/no-go deployment decision or an audit/sign-off.

jassics/awesome-claude-security

Plugin Claude Code

Trustworthy-AI suite: one-shot install pairing AI safety with the full GenAI security stack (ai-safety + genai-suite).

jassics/awesome-claude-security

Plugin Claude Code

AI safety (not security): harm modeling, safety evaluations, responsible red-teaming, bias/fairness, guardrail review, and responsible-AI governance.

jassics/awesome-claude-security

Agent

Senior AI safety reviewer for an end-to-end SAFETY assessment of a model or feature — harm modeling, safety evaluation, responsible red-teaming, bias/ fairness, guardrails, and responsible-AI governance. Use for a full safety review (about harm to people/society), distinct from a security review (about attackers).

jassics/awesome-claude-security

Skill Claude CodeCodex

Assess an AI model, feature, or dataset for bias and fairness across groups — representational and allocative harms, disparate performance, and skewed refusals — using appropriate fairness metrics, and recommend mitigations. Use when evaluating whether an AI system treats people equitably.

jassics/awesome-claude-security

Skill Claude CodeCodex

Review or design the content-safety guardrails of an AI system — input/output classifiers, refusal and safe-completion behavior, escalation/human handoff, and coverage across harm categories, languages, and modalities. Use when assessing or building the safety controls around a model.

jassics/awesome-claude-security

Skill Claude CodeCodex

Systematically enumerate the potential HARMS of an AI system — to users, third parties, vulnerable groups, and society — under normal use, misuse, and malfunction, then rank them and map mitigations. This is the AI-safety analog of threat modeling (which targets attackers). Use when designing or reviewing an AI…

jassics/awesome-claude-security

Skill Claude CodeCodex

Gap-assess an AI system or program against a responsible-AI / governance framework — NIST AI RMF, ISO/IEC 42001, EU AI Act, OECD principles — covering governance, transparency, accountability, human oversight, documentation, and monitoring, then produce a prioritized roadmap. Use for AI governance, audit readiness, or…

jassics/awesome-claude-security

Skill Claude CodeCodex

Design and run a safety evaluation suite for an AI model or feature across harm categories — refusals on disallowed content, robustness, over-refusal vs helpfulness, groundedness/truthfulness — with rubrics and pass/fail thresholds. Use to measure an AI system's safety, establish a baseline, or gate a release.

jassics/awesome-claude-security

Skill Claude CodeCodex

Responsibly red-team an AI system to find SAFETY failures — harmful outputs, jailbreaks that defeat safety guardrails, and foreseeable-misuse / dangerous- capability elicitation — so they can be mitigated. Use to stress-test safeguards before/after release. Controlled, authorized, mitigation-focused; not for producing…

jassics/awesome-claude-security

Plugin Claude Code

API security testing: OWASP API Security Top 10 assessment and object/function-level authorization (BOLA/BFLA) testing.