Test design, vulnerability assessment, and quality assurance (13K skills)
Creates custom Semgrep rules to detect vulnerabilities, bug patterns, or coding standard violations. Builds tests for unsafe and safe examples, then validates and refines each rule to check for false alarms and missed cases.
Review TON smart contracts written in FunC for three security patterns: incorrect boolean values, unverified Jetton token notifications, and forwarding funds without reserving execution fees. Receive a coverage table, source references, severity ratings, and suggested fixes.
Review token contracts and the protocols that accept them for ERC20/ERC721 compliance, privileged controls, and unusual transfer behavior. Produces evidence-based risk assessments and prioritized fixes, with supply and holder analysis when deployed contract details are provided.
Inspects compiled instructions and bytecode to identify timing risks in cryptographic code. Helps trace flagged operations back to secret data, distinguish false positives, and review fixes across compiler settings and target architectures.
Review Substrate and Polkadot runtime modules, called pallets, for seven security patterns, including unsafe arithmetic, crashes, incorrect processing costs, and weak permission checks. Produce a complete coverage table, findings with code references, and proposed fixes.
Maps externally callable smart contract functions that change stored data, then groups them by access restrictions. Produces a structured audit report showing public functions, privileged operations, and access checks that need further review.
Scans code for security vulnerabilities with CodeQL by tracing data across functions. Builds and checks analysis databases, models project-specific APIs, and saves findings in SARIF, a structured results format, with broad or focused scan options.
Port an existing Semgrep rule to specified programming languages, producing separate rule and test files for each. The skill checks applicability, adapts detection patterns to each language, and reports validation results.
Audit npm, PyPI, and Go dependencies for version-specific advisories, inactive upstream projects, concentrated npm publishing rights, and installation scripts. Produce a report backed by collected data, with assessment coverage, action priorities, and upgrade or replacement guidance.
Search HTTP traffic and security findings stored in Burp Suite project files from the command line. Filter response headers or bodies with text patterns, extract affected URLs, and review selected proxy history or site map data.
Assess test strength by introducing deliberate code changes with mewt or muton. Configure test runs, examine changes that tests miss, distinguish harmless equivalents from testing gaps, and investigate potential bugs in the affected code.
Review Solana and Anchor programs for six security patterns, including unsafe calls to other programs and missing account checks. Receive a complete coverage table, findings with file references and severity, and suggested fixes for identified issues.
Audits arithmetic code for mixed units, decimal precision mistakes, and scaling errors. Adds comments identifying each value’s units and produces a summary of findings, unit definitions, and files reviewed.
Build a documented understanding of unfamiliar code before a security audit. It records function assumptions, guarantees, dependencies, and open questions, producing a dossier and individual function notes to support later vulnerability analysis.
Prepare a codebase for an external security review by defining goals, running static checks, improving test coverage, and removing unused code. Assemble the review scope, verified build instructions, diagrams, and documentation into a package for auditors.
Reviews code changes for security risks using Git history, caller counts, and test coverage. Produces a Markdown report with evidence, potential attack scenarios, affected code, and clear limits on what was reviewed.
Writes, reviews, and debugs property-based tests, which generate inputs to check general rules. Helps test conversions, parsers, normalization, and state invariants, assess whether existing assertions are meaningful, and distinguish faulty rules from implementation bugs.
Reviews APIs and configuration designs for choices that make security mistakes easy. Checks unsafe defaults, confusing parameter types, and hidden failures, then validates whether misuse creates a real vulnerability and assigns severity.
Compare implementation code with a specification, whitepaper, or design document. It checks individual requirements, independently challenges reported mismatches, and writes evidence-based reports covering missing or partial implementation, contradictions, undocumented behavior, and requirements that cannot be judged.
Process SARIF files, a standard format for static analysis results, to filter alerts, remove duplicates, combine findings from multiple tools, and produce reports. It also supports comparing runs and integrating result checks into CI/CD pipelines.
Scan source code for security weaknesses with Semgrep after approving the target and rulesets. Choose full results or focus on important findings, then receive merged results and a record of failed or skipped scans.
Assesses smart contract and blockchain codebases against Trail of Bits’ nine-category maturity framework. Produces evidence-backed ratings covering areas such as arithmetic, access controls, documentation, and testing, plus a prioritized improvement roadmap with effort estimates.
Check whether a file creation or transformation task actually succeeded after an unclear execution error. Inspect output files and their contents to distinguish success, partial completion, and failure before deciding whether to retry.
Check files created or edited by another agent, subprocess, or tool against explicit requirements. Verify the actual location, structure, counts, and key fields, then rerun with absolute paths when the results contradict the completion report.