AutoGineer
Generated banner for Hunt Regressions
Generated logo for Hunt Regressions

Hunt Regressions

Trail of BitsOfficialPublished by Trail of Bits

  • Skill
  • Review and audit
  • Security
  • CC-BY-SA-4.0
  • No issues found
Download ZIP

From the author

Use when discovering possible regressions from a pinned change and its callers before reproduction.
— the description by Trail of Bits

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The hunt-regressions skill provides a structured methodology for analyzing code changes to uncover potential regressions. It focuses on tracing changed behavior through callers to real interfaces, ensuring that analysis remains grounded in the original intent and supported use cases. By requiring adherence to specific definitions and file contracts, the skill ensures that findings are documented with sufficient context for later verification, while explicitly separating the discovery phase from the proof-of-concept construction.

What it does

  • Analyzes code diffs to trace changed behavior through system callers.
  • Verifies changes against original intent and security documentation.
  • Records potential defects, reachable triggers, and false-positive checks.
  • Registers identified candidates with stable hypothesis keys.
  • Produces a structured report including coverage gaps and identified leads.
  • Enforces a strict separation between discovery and reproduction.

When to use it

  • When you need to identify potential regressions introduced by a specific code change.
  • When analyzing the impact of a change on system callers before attempting reproduction.
  • When you have a frozen change context and need to map potential defects.
  • When you need to document coverage gaps and uninspected areas for a given change.

Advantages

  • Prevents premature assumptions by requiring evidence-based tracing.
  • Standardizes the documentation of potential defects for easier hand-off to reproduction.
  • Reduces noise by rejecting unsupported hypothetical failure scenarios.
  • Ensures consistent tracking of leads through a registry system.

Usage examples

“Analyze the provided diff for potential regressions in the authentication module.”
The agent reviews the diff, traces the changes through the caller interfaces, and returns a list of registered candidate IDs with associated coverage details.
“I have a frozen change context; please hunt for regressions.”
The agent verifies the preparation, performs the analysis based on the provided registry assignment, and reports the count of identified candidates.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/trailofbits/hunt-regressions/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip hunt-regressions.zip -d .agents/skills

Documentation by Trail of Bits

Discover candidates

When to Use

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.

When NOT to Use

Proving a known candidate; use reproduction. Discovery cannot confirm findings.

Hunt

  1. Read the standard and file contract. Verify preparation; read frozen change messages, PR discussion and security documentation for intent and supported use.

  2. Review the entire diff; trace changed behavior through callers to real interfaces. Use frozen sources and supplied context, not later fixes, advisories or other reviews.

  3. Record each lead's changed code, previously supported behavior, reachable trigger, proposed new defect, false-positive checks and required proof. Retain supplied leads suggesting old bugs or incomplete fixes for adjudication. Leave PoC construction to reproduction.

  4. Reserve each lead's ID through registry.py 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.

Report Back

Keep detailed evidence in the sealed package. Return only:

  • Status: complete or blocked, matching the record.

  • Record: sealed hunt.json path, or why none was produced.

  • Result: candidate count and material coverage gaps.

  • Blocker: missing prerequisite or required caller action, if blocked.

Rationalizations to Reject

  • “A helper fails on invented input”: show a supported interface that reaches it.

Files

ATTRIBUTION.md

Attribution

This folder is an unmodified copy of the Agent Skill "hunt-regressions", distributed by AutoGineer (https://autogineer.com/agent-skills).

The skill's own files are unmodified copies. AutoGineer is not affiliated with or endorsed by the author or the publisher.

Files added by AutoGineer

  • ATTRIBUTION.md: this file, written by AutoGineer

  • LICENSE: copied from LICENSE

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Trail of Bits
Publisher
Trail of Bits (Official)
Source
trailofbits/skills · plugins/regression-hunt/skills/hunt-regressions · commit e4dd0bb
Licence
Creative Commons Attribution-ShareAlike 4.0 International (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Trail of Bits or Trail of Bits.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download hunt-regressions.zip