Security & Testing Agent Skills for Cursor

Reference: https://cna.erlef.org/cve-criteria Verify the case specified by the user (or the current working case).

Medical device cybersecurity risk assessment skill per FDA premarket and postmarket guidance

This skill should be used when the user asks "how complex is this function", "count the branches", "find overly complex functions", "set a…

Run checks (lints, tests, etc.) using Dagger scafolding

DAO governance attack — flash-loan-backed vote manipulation, delegation hijack, quorum dilution, proposal-spam DoS, time-lock bypass via…

Audits one page against the accessibility criteria that can be checked from markup, names the WCAG success criterion behind each finding…

Process use when you need to work with security and compliance.

Use this skill to run DataHub's saved evals and report answers for judging.

Toolkit for interacting with and testing local web applications using Playwright.

Augments Trailmark code graphs with external audit findings from SARIF static analysis results and weAudit annotation files.

Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state…

Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts…

Builds and queries multi-language source code graphs for security analysis.

Runs full Trailmark structural analysis on Trailmark 0.2.x by building a graph, running `preanalysis()`, and reporting hotspots, taint…

Find similar vulnerabilities and bugs across codebases using pattern-based analysis.

Debugging specialist for errors, test failures, and unexpected

Advanced debugging integration for vulnerability research

Debug computerd in real-FUSE mode end-to-end without workerd, vitest-pool-workers, or wrangler in the loop.

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence…

Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical…

Use when a test fails, a bug is reported, or observed behavior does not match expectation, and before proposing or applying any fix.