테스트·보안 스킬

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for issue filing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyzes CVE vulnerabilities in project dependencies with code path tracing and PoC generation for Burp Suite. Traces vulnerable code from user input to sink, assesses exploitability, and generates HTTP requests for testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute a complete Active Directory penetration test from initial enumeration to domain dominance. Use this skill for AD security assessments including LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP roasting), BloodHound attack path analysis, credential dumping with Mimikatz, lateral movement via PsExec/WMI/DCOM, DCSync for NTDS extraction, and Golden/Silver ticket forging. Covers the full kill chain from domain user to domain admin.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bug bounty findings secretary, tracker, and workspace initializer for the bb-huge portal. Use this skill for web security research, vulnerability hunting, and hunt workspace setup. Triggers on: "log finding", "save finding", "add to bb-huge", "record vulnerability", "update finding", "show findings", "bb-huge stats", "mark as confirmed", "mark as rewarded", "setup workspace", "pull evidence", "continue working on finding", "dump attachments", "list my skills", "what skills do I have", "/bb-huge init", "init hunt workspace", "new bug bounty program", "start hunting", "mobile bug bounty", "binary analysis", "source code review", "white-box audit", "h1-brain", "hack program", "hack()", "search disclosed", "fetch rewarded". Also auto-activates whenever a vulnerability is discovered during any recon, fuzzing, or manual testing session — do not wait to be asked.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when designing, auditing, or troubleshooting behavioral boundaries for Agentforce agents — including topic (now subagent) Scope fields, agent-level system instructions, topic/action filters, the Escalation topic, restricted topics, and Instruction Adherence monitoring. Trigger keywords: agent guardrails, agent out of scope, restrict agent behavior, topic scope, subagent scope, agent fallback, Escalation topic, abuse prevention, action filters. NOT for Trust Layer content filtering (Einstein Trust Layer is a separate product concern), NOT for general topic routing design (use agentforce/agent-topic-design), NOT for prompt template construction (use agentforce/prompt-builder-templates).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when practitioners need to understand system-managed fields (CreatedDate, LastModifiedDate, SystemModstamp, CreatedById, LastModifiedById, IsDeleted) — their update behavior, indexing, and queryability. Triggers: 'difference between SystemModstamp and LastModifiedDate', 'how to query deleted records', 'set CreatedDate during data migration', 'why does LastModifiedDate not match SystemModstamp', 'Create Audit Fields permission'. NOT for a field's value-change history — use data/field-history-tracking. NOT for Shield Field Audit Trail — use security/field-audit-trail.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when writing acceptance criteria for Salesforce features, structuring UAT test scripts from user stories, classifying defects found during UAT, or planning regression testing before a Salesforce release. Trigger keywords: UAT, user acceptance testing, test script, acceptance criteria, defect classification, regression testing, test plan, test case. NOT for Given/When/Then AC syntax — use admin/acceptance-criteria-given-when-then. NOT for the per-case field schema and AC-to-case decomposition — use admin/uat-test-case-design. NOT for automated Flow or Apex test coverage — use flow/flow-testing. Also covers: UAT plan record, sandbox selection for UAT, pre-UAT environment checklist, sandbox email deliverability for testers, test-user personas, negative and bulk coverage, defect triage categories, go/no-go sign-off, quick-deploy window.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Author and run offline evals for Agentforce agents: fixture format, scoring rubrics, hallucination checks, regression baselines, CI integration, prompt-change safety. Trigger keywords: agent eval, hallucination, doesn't hallucinate, agentforce offline evals, rubric for agent response. NOT for deciding which layers of testing the agent needs — use agentforce/agentforce-testing-strategy. NOT for Testing Center, AiEvaluationDefinition or sf agent test runs — use agentforce/agent-testing-and-evaluation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

An Agentforce agent is moving from build or sandbox to live end-user traffic and the team needs a comprehensive readiness gate: coverage testing, Trust Layer config, guardrails, cost telemetry, observability, rate limits, permissions, rollout strategy, rollback plan, performance benchmarks. Triggers: 'we want to ship our Agentforce agent next week', 'pre-prod readiness review for our Service Agent', 'what do we need before turning the agent on for real customers', 'agent went live and is hallucinating, what should we have caught', 'cost monitoring for our internal sales agent', 'rollout strategy from internal pilot to GA'. NOT for the lighter five-block activation sign-off artifact — use agentforce/agent-deployment-checklist. NOT for authoring the guardrails themselves — use agentforce/agentforce-guardrails. NOT for building the test harness — use agentforce/agentforce-eval-harness. NOT for Trust Layer feature setup in isolation — use agentforce/einstein-trust-layer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design Invocable Apex actions that return deterministic, agent-friendly errors instead of surfacing raw exceptions to the LLM. NOT for authoring the action itself — @InvocableMethod schema, labels, security context — use agentforce/custom-agent-actions-apex. NOT for the Apex tests that force each error branch — use agentforce/agent-action-unit-tests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Redact PII in your own code before it reaches Agentforce prompts, models, and logs. Trigger keywords: agentforce pii, pii redaction, data masking llm, prompt pii filter, audit pii leakage. NOT for turning on the platform's own masking, zero-retention and audit-trail controls — use agentforce/einstein-trust-layer. NOT for masking PII in a refreshed sandbox — use security/sandbox-data-masking.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when designing the human-executable UAT test cases that prove a Salesforce feature works for a specific persona — the per-persona scripts with preconditions, data setup, permission setup, ordered steps, and pass/fail evidence that close out an RTM row. Trigger keywords: UAT test case salesforce, user acceptance test script salesforce, manual test salesforce feature, UAT script per persona, UAT precondition data setup, UAT permission set assignment for testing, negative path UAT case. NOT for high-level UAT planning, defect classification, regression strategy, or sign-off (use admin/uat-and-acceptance-criteria). NOT for the Given/When/Then technique used to write the AC the case is derived from (use admin/acceptance-criteria-given-when-then). NOT for Apex test method generation (use agents/test-class-generator). NOT for test data factory patterns (use templates/apex/tests/TestDataFactory.cls). NOT for performance or load testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when designing or reasoning about an Agentforce Grid worksheet — the spreadsheet-like Agentforce workspace where rows are jobs and columns are sequential Data / AI / Action steps that process left to right — to run bulk record updates, generate insights, or test multi-turn AI conversations over CRM or Data Cloud (Data 360) data without Apex or Flow. Trigger keywords: Agentforce Grid, workbook, worksheet, grid column, data column, AI column, action column, bulk AI update, Flex Credits per row, metered compute. NOT for building the agent, its topics, or its actions themselves (use agentforce/* action and topic skills), NOT for single-record prompt design (use the prompt-builder skills), NOT for deployable metadata/Apex (Grid is a no-code Studio tool, not a metadata type), and NOT for AI governance/ethics policy (use admin/ai-ethics-and-governance-requirements).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when testing, evaluating, or building regression suites for Agentforce agents: conversation testing in Agent Builder, topic (now subagent) coverage and utterance testing, Testing API and AiEvaluationDefinition metadata, Agentforce DX CLI test runs (sf agent generate test-spec, sf agent test create/run/resume/results/list), evaluation metrics (containment rate, escalation rate, CSAT, topic activation accuracy), and post-deploy analytics via Enhanced Event Logs. Triggers: 'how do I test my Agentforce agent', 'agent routes to wrong subagent', 'write utterance tests', 'regression test after topic change', 'measure agent quality', 'agent containment rate', 'run agent tests from the CLI'. NOT for agent creation, topic design, or action contract design — use agentforce/agentforce-agent-creation, agentforce/agent-topic-design, or agentforce/agent-actions respectively.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pre-production security checklist for Agentforce deployments: agent run-as permission scope, grounding-source data classification, action write-scope, audit trail. NOT for the full go-live readiness gate covering cost telemetry, rate limits, rollout and rollback — use agentforce/agentforce-production-readiness-checklist. NOT for a general org security review — use security/security-health-check.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Configuring User Access Policies (UAP) to automatically assign or revoke permission sets and permission set groups based on user attributes. Use when automating permission provisioning on user create/update without Apex triggers. Covers policy configuration, filter criteria, evaluation order, and PSL assignment. Also covers booleanFilter OR logic, the `in` operator for multi-value filters, the `order` tiebreak between competing policies, actions incl. permission set / permission set group / permission set licence / package licence / queue / public group grant and revoke, the UserAccessChange audit object, and deploying the UserAccessPolicy metadata type. NOT for permission set design — use admin/permission-set-architecture. NOT for delegated user admin — use admin/delegated-administration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apex test patterns for @InvocableMethod agent actions: per-reason-code branch coverage, bulk safety, callout mocking, deterministic assertions. NOT for testing whether the agent routes to the right topic or answers well — use agentforce/agent-testing-and-evaluation. NOT for designing the error envelope the tests assert on — use agentforce/agent-action-error-handling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing, auditing, or troubleshooting Salesforce Validation Rules. Triggers: 'validation rule', 'required field formula', 'rule fires unexpectedly', 'integration failing validation', 'data quality', 'errorConditionFormula', 'errorDisplayField', 'errorMessage 255 characters', 'ValidationRule metadata', 'validationRule-meta.xml', 'deploy validation rule inactive', 'bypass custom permission', 'FIELD_CUSTOM_VALIDATION_EXCEPTION', 'validation rule on custom metadata type', 'compound field validation rule', 'require at least one child record before a stage', 'HasOpportunityLineItem'. NOT for Flow-based validation — use admin/flow-for-admins for that.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when building, reviewing, or refreshing a RACI (Responsible / Accountable / Consulted / Informed) matrix for a Salesforce project so that every Salesforce-specific decision — data model change, automation tier choice, security model, integration boundary, deployment, license/edition — has exactly one accountable owner and a documented escalation path that downstream agents can route to. Trigger keywords: RACI matrix salesforce project, stakeholder authority salesforce, escalation path salesforce decisions, who approves data model change, salesforce decision rights, REFUSAL_NEEDS_HUMAN_REVIEW routing. NOT for the change advisory board operating model itself (use admin/change-management-and-deployment). NOT for end-user training rollout plans (use admin/change-management-and-training). NOT for the technical mechanics of permission set assignment authority (use admin/permission-set-architecture). NOT for pure stakeholder requirements elicitation (use admin/requirements-gathering-for-sf). More trigger keywords: who approves a sandbox refresh, who signs off a data load, release update activation owner, delegated admin authority vs RACI, multi-org decision rights, escalation time-box.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when an ISV or consulting partner is creating, pricing, publishing, or maintaining an AgentExchange listing through the Partner Console — covers the listing plan, the 5-step Listing Builder workflow (Fill in the Basics, Set Pricing, Add Details, Link Your Solution, Grow Your Business), commercialization models (revenue share vs. annual fee vs. freemium), AgentExchange Checkout setup (Stripe connection, pricing plans, fees, geographic eligibility), Private Offers, Security Review gating, and post-publish listing updates. NOT for building the agent or managed package itself (use agentforce/agentforce-agent-creation and devops/second-generation-managed-packages), NOT for LMA/Trialforce licensing internals (use devops/isv-license-management-and-trialforce), and NOT for the customer-side install experience.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Authoring and managing Agentforce agent definitions using the declarative Agent Script DSL (.agent files) and associated metadata types, including the Agent Script language for the new Agentforce Builder (hybrid-reasoning -> logic vs | prompt instructions, @actions/@subagent/@variables references, subagents). Use when creating agents in source control, writing or debugging Agent Script, debugging agent metadata, or understanding the metadata lifecycle of GenAiPlugin/GenAiPlanner/BotVersion types. Triggers: 'write or debug Agent Script', 'how do I deploy an Agentforce agent using source control', 'convert an agent topic to a subagent', 'what metadata types make up an Agentforce agent', 'agent test run command failing in CI pipeline', 'GenAiPlugin vs GenAiPlanner metadata relationship', 'Agent Script logic vs prompt instructions'. NOT for Apex-based agent actions — use agentforce/custom-agent-actions-apex. NOT for clicking the agent together in the Builder UI — use agentforce/agentforce-agent-creation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.