Review a specific code change and trace its callers to identify behavior that may have broken. Record suspected regressions, reachable triggers, evidence needs, and coverage gaps so a separate reproduction step can investigate them.
Use when discovering possible regressions from a pinned change and its callers before reproduction.
Review the instructions the agent will receive before you install.
Input: sealed preparation, frozen S0/S1, change context and registry assignment. On retry, include this assignment's prior candidate-ID mapping. The caller supplies these, including for independent use. Follow project guidance before target work.
Proving a known candidate; use reproduction. Discovery cannot confirm findings.
candidate
using its stable hypothesis key and assigned agent handle. Reuse the key on retry.
Write candidate files and hunt.json with IDs, file mappings, coverage and limitations.
An empty list is valid.
If blocked, record partial coverage and uninspected areas. Seal the package.Keep detailed evidence in the sealed package. Return only:
complete or blocked, matching the record.hunt.json path, or why none was produced.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Build and test code with AddressSanitizer, a tool that detects invalid memory access during execution. Configure checks for C/C++ and unsafe Rust, investigate crash reports, and adjust settings for fuzzing, or testing with generated inputs.
Assess source code and live reproduction evidence to decide whether a change introduced a regression, a newly caused defect. Record supported conclusions, exclusions, severity, and unresolved gaps in an evidence-linked decision file.
Sets up AFL++ to test C/C++ programs with varied generated inputs, a technique called fuzzing. Covers running tests across CPU cores, monitoring progress, reducing input collections, and reproducing crashes for investigation.
Audits GitHub Actions workflows that run AI coding agents. Traces how attacker-controlled content reaches prompts, checks permissions and sandbox settings, and reports evidence, severity, and fixes for prompt injection and related configuration risks.
Reviews Algorand smart contracts written in TEAL or PyTeal for 11 vulnerability patterns. Produces a complete coverage table and findings with code references, severity ratings, and suggested fixes, with optional automated checks using Tealer.
Set up Atheris to test Python code and C extensions with automatically varied inputs. It guides test harness creation, coverage tracking to explore more code, and AddressSanitizer setup for finding memory errors.