Test design, vulnerability assessment, and quality assurance (13.1K skills)
Build repeatable evaluations for AI agent responses, tool choices, and multi-step tasks. Use reference datasets and scoring criteria to compare changes, detect quality regressions, and set automated checks that must pass before deployment.
Review pull requests, branches, commit ranges, or local changes with GitNexus. Combine code relationship analysis with source and test inspection to identify concrete defects, missing tests, affected behavior, and risks before merging.
Understand and extend GitNexus taint analysis, which tracks data from input sources to potentially dangerous operations. Use its implementation guidance to investigate missed or incorrect findings, add detection models, and validate analysis changes.
Create a disposable Herdr session to reproduce terminal, process, API, or agent issues separately from the main session. Drive tests through the CLI or API, collect evidence of state changes, and clean up the temporary session afterward.
Check token security audit data before buying or swapping crypto. Review contract and trading risks, buy and sell taxes, and signs of scams such as tokens that can be bought but cannot be sold.
Explore a web application as a user to find reproducible bugs and usability problems. Produce a structured report with reproduction steps, screenshots, and videos for interactive issues, giving responsible teams concrete evidence to investigate.
Scan a codebase or selected changes for security issues, then request targeted patch files for findings. Independent agents verify reported issues and proposed fixes, while you review and apply patches yourself.
Manage access to a Discord channel integration by approving pairing codes, updating allowed users, and setting direct-message and channel policies. Check pending requests and adjust reply behavior through configuration files read by the channel server.
Manage access to a Telegram channel integration by approving pairing codes, updating allowed users, and setting direct-message and group policies. Check pending requests and adjust reply behavior through configuration files read by the channel server.
Investigate prompt injection in sandboxed security challenges by tracing how untrusted text changes an agent’s decisions or tool calls. Build a minimal reproduction and preserve evidence showing where external content crosses into trusted instructions or actions.
Reproduce timing and ordering bugs in a CTF sandbox using controlled concurrent requests. Compare normal and racing runs, trace reads and writes, and preserve a minimal sequence that demonstrates duplicate actions or inconsistent state.
Organize CTF investigations by mapping the supplied targets, tracing one minimal path, and selecting the relevant specialist workflow. Findings are grounded in observed behavior and reproducible evidence, with a clean baseline used for verification.
Investigate Windows secrets protected by DPAPI, a system for encrypting sensitive data, in a CTF sandbox. Trace the required keys and account context through decryption, then verify which service accepts the recovered secret.
Examine Windows credential material in a CTF sandbox, including LSASS memory and Kerberos tickets. Distinguish stored secrets from credentials that actually work, and document the evidence linking their source to successful authentication or resulting privileges.
Compare how proxies and backend servers interpret HTTP requests in a CTF sandbox. Use paired requests and logs to pinpoint differences in paths, headers, or message boundaries, then document a minimal reproduction of unintended routing.
Analyze packet captures in a CTF sandbox by rebuilding communication sessions and decoding message contents. Recover transferred files and connect packet order, timing, and reconstructed streams to observed host or malware behavior.
Trace uploaded files through extraction, conversion, parsing, and reconstruction of saved objects in a CTF sandbox, an isolated competition environment. Preserve original and derived files, distinguish visible validation from backend behavior, and document the smallest reproducible processing chain.
Trace SSH keys, tokens, and other credentials in Linux CTF environments. Connect each recovered artifact to the service that accepts it, then document the resulting privileges or movement to another host.
Trace how requests become rendered pages in a CTF sandbox. Compare display restrictions with server enforcement, inspect data passed to the browser, and preserve a minimal example that demonstrates where rendering behavior diverges.
Trace how requests travel through a CTF sandbox, from hostnames and proxy rules to containers and processes. Compare headers and live traffic to identify which service handles a request and what changes its destination.
Compare GraphQL and RPC contracts, which describe expected API behavior, with generated clients and live handlers in a CTF sandbox. Identify hidden or outdated operations and preserve minimal request pairs that demonstrate the mismatch.
Analyze running iOS apps in a CTF sandbox, a controlled challenge environment. Trace methods, inspect secure storage, and examine request signing and certificate checks to identify the state needed to reproduce an accepted request.
Recover hidden malware settings and communication parameters in an isolated CTF environment. Document how values are decoded, preserve supporting evidence, and connect recovered fields to the sample’s observed behavior.
Trace software artifacts from source and dependencies through builds, publishing, and runtime use in CTF sandboxes. Compare intended versions with shipped files to identify the earliest divergence and document the evidence linking each stage.