vulns.co
/
GKData.io MCP
RE / Research

Research handoff

Package local hunt state so another researcher or client can resume from evidence, gaps, and ranked actions without repeating work.

Guide 22 / 223 review notesUpdated 2026-10-12
Download .md ↓JSON ↗

The review

What to look for

Defensive study and review of artifacts supplied by their owner. Record missing evidence as an open question.

  1. Review the state

    Use search_hunt_records to confirm scope references, assets, check states, leads, activity, and evidence links. Preserve partial, blocked, failed, and not_tested work as useful history.

  2. Rank continuation work

    When a local Hunt Workbench is available, call next_actions for a short ranked set of gaps and leads. Its rationale may reference public vulns.co research, while workspace evidence remains local.

  3. Export without overstating

    Call export_handoff for a concise Markdown brief. It must cite underlying records and label leads as hypotheses until validated evidence supports a finding.

What to produce

  • Evidence-linked Markdown handoff
  • Coverage and blocker summary
  • Ranked next actions with rationale

Common mistakes

  • Hiding incomplete or failed work
  • Leaving scope references out of the handoff
  • Describing a hypothesis as a confirmed vulnerability

Use with MCP

Take this into the workbench.

The hosted MCP reads public research. The separate local Hunt Workbench saves private project records in your chosen directory.

Public context

get_research_context search_research get_research_record

Local record tools

next_actions export_handoff search_hunt_records

Connection and local install guide ↗

Continue the study

Reading & source context

Editorial notes above connect these references. Open each record for its original source and review date.

Quality ReportsHackerOne Help Center OWASP Logging: trustworthy and minimal application evidenceOWASP Cheat Sheet Series OWASP Secure Code Review: baseline and change-focused reviewOWASP Cheat Sheet Series

Visual models

Reviewed content and its immutable version are bound to an approval. Execution independently checks that the version still matches. Matching requests proceed with least privilege; mismatches require a new review.Approval stays attached to the reviewed version ↗

Connected disclosures

Cloud Build approval was not bound to immutable codeGoogle GitHub Actions trust depended on invalid repository referencesGitHub

From the field toolkit

Writing a Report That Survives Triageplaybooks ↗Before you submitchecklists ↗

Guide by GK Data · Research snapshot 2026-10-04.
Sources and review dates are preserved in the library provenance.

Next skillScope and intake →