Security & Testing Agent Skills

Use when evaluating, ranking, monitoring, or selecting LLM/agent outputs or trajectories with explicit criteria, especially when…

Harden an LLM application against unbounded consumption with input/output caps, token budgets, rate limiting, and cost controls.

Constrain an LLM application to answer only from retrieved, verifiable grounding — enforce citations, validate that cited sources support…

Turn unsanitized LLM output into code execution or injection in the downstream sink that consumes it — XSS in a browser, SQL in a query, a…

Elicit confident, ungrounded fabrications from an LLM application — invented facts, fake citations, non-existent policies — and show they…

Detect direct and indirect prompt-injection attempts and successful policy breaks against an LLM application from prompt/response telemetry.

Elicit sensitive information an LLM application should not reveal — training data, other users' data, secrets pulled into context, or…

Extract an LLM application's hidden system prompt and any secrets embedded in it during an authorized assessment.

Validate load balancer behavior, failover, and traffic distribution.

Generate load test scripts for k6, Locust, and Gatling from OpenAPI specs

Review local git changes from 8 expert perspectives by spawning the matching reviewer subagents in parallel.

Implement Lokalise translation data handling, PII management, and compliance

Mandates fresh verification evidence before any completion claims.

Security Basics for Lucidchart.

Reviews code for objective correctness, security, and reliability.

Map an unfamiliar test program's active launch, flows, dependencies, variants, evidence, and durable product context.

Decompiles, modifies, repacks, and dynamically instruments Android APK applications using CLI tools like JADX, Apktool, and Frida.

Migrates reverse engineering symbols, offsets, and function names across binary versions using automated LLM-assisted diffing.

Use test-driven development when the user asks for test-first work, red-green-refactor, integration tests, or when a requested…

When to activate: Rust tests, unit tests, integration tests, doc tests, benchmarks, proptest, test helpers, test organization

JVM dependency intelligence via Maven Tools MCP server.