Runsybil Changelog: August 2026

html<table style="border-collapse: collapse; font-size: 13px; width: 100%; margin: 0 auto;">
  <thead>
    <tr>
      <th style="border: 1px solid black; padding: 4px 6px;"></th>
      <th style="border: 1px solid black; padding: 4px 6px;">Delta TPs</th>
      <th style="border: 1px solid black; padding: 4px 6px;">Full TPs</th>
      <th style="border: 1px solid black; padding: 4px 6px;">Total TPs</th>
      <th style="border: 1px solid black; padding: 4px 6px;">Likely FPs</th>
      <th style="border: 1px solid black; padding: 4px 6px;">Likely FP Rate</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td style="border: 1px solid black; padding: 4px 6px;">Claude<br>Code</td>
      <td style="border: 1px solid black; padding: 4px 6px;">44 / 46<br>(95.7%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">19 / 50<br>(38.0%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">62 / 95<br>(65.3%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">48</td>
      <td style="border: 1px solid black; padding: 4px 6px;">43.6%</td>
    </tr>
    <tr>
      <td style="border: 1px solid black; padding: 4px 6px;">Codex<br>(GPT-5.5)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">43 / 45<br>(95.6%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">30 / 50<br>(60.0%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">74 / 95<br>(77.9%)</td>
      <td style="border: 1px solid black; padding: 4px 6px;">629</td>
      <td style="border: 1px solid black; padding: 4px 6px;">89.5%</td>
    </tr>
  </tbody>
</table>
<p style="font-size: 12px; font-style: italic; margin-top: 8px;">Table 2: True positive (TP) and false positive (FP) analysis of Claude and Codex across challenge types.</p>

Table of contents

*H2 Required

OWASP Top 10 Coverage: New interactive view mapping test activity to OWASP Top 10 standards.
AI-Generated Executive Summary: Enhanced reporting with automated, easy-to-read executive summaries for completed projects.
Flexible Credential Setup: Improved account management with support for non-standard login flows and custom fields.
New Productivity Features: Added support for scheduled recurring tests, Markdown report exports, and change-based finding context for faster pentesting workflows.

END SUMMARY

Welcome to our first RunSybil monthly update! Our team has been hard at work behind the scenes listening to customer feedback and building out features to make your testing experience even smoother. This month, we’ll spotlight our OWASP Top 10 summary tab. Plus, we've rolled out other quality-of-life improvements, and have some exciting ideas on the roadmap coming up.

Spotlight Feature: OWASP Top 10 Coverage

If there’s one thing that being in the pentesting business has taught me over the years, it’s that everyone speaks in the language of the OWASP Top 10. That’s why we’ve added a convenient view of how your most recent test activity maps to the OWASP Top 10.

*Figure 1: OWASP Top 10 Coverage view mapping recent test activity.*

New Executive Summary

Along the same lines as the OWASP Top 10 view, we understand customers want simple readouts that summarize testing activity to an executive audience. That’s why we’ve also refined our reporting process to include an AI-generated executive summary, also available on completed projects/tests.

*Figure 2: Example of an AI-generated Executive Summary for a completed project.*

More Flexible Login/Credentials Setup

We’ve added new account setup options to support customers with non-standard login flows, including per-account login instructions and custom fields for application-specific data like class codes, tenant IDs, or access tiers. Sensitive values are protected in planning and reporting contexts while remaining available to the agents that need them to complete login and testing.

*Figure 3: New account setup options supporting non-standard login flows and custom fields.*

More Updates & Enhancements

Scheduled Tests: Customers can now schedule recurring tests, making it simple to set up a test cadence for every quarter, month or week in one sitting.
Markdown Report Exports: Customers can now download reports in Markdown, making it easier to share Sybil results in docs, internal workflows, and customer-facing writeups without reformatting from PDF, JSON, or CSV.
Change-Based Finding Context: Sybil now links findings from change-based tests back to the relevant changed file or code area, giving customers clearer context on why a finding was generated.

Coming Up On The Roadmap

Integration support: Push findings into systems you’re already working in - Jira, GitHub and Linear.
WAF Detection: Reducing test setup friction by notifying users when a WAF is detected by RunSybil, so there are no surprise limitations to attack traffic.
Scope Recommendations: Start tests faster by automatically identifying scope issues and suggesting what should be accessible, attackable, or off-limits before a test begins.
User Tags: Tag by team, franchise, business unit - whatever meets your organizational needs.
Knowledge Base Ingestion: Confluence, Notion, GDocs syncs that RunSybil agents reference during testing for a more thorough white box approach.
Resilient Test Traffic: Improve reliability by giving tests dedicated backup egress IPs, reducing the risk that one blocked or overloaded connection disrupts customer testing.

Wrapping Up

That’s all for this month! We hope these updates make your experience with RunSybil even better. As always, your feedback is what drives our roadmap. If you have any suggestions, questions, or just want to say hi, feel free to reach out or subscribe to get our monthly changelog by email.

FAQ

Recent product questions we wanted to surface:

Will RunSybil be adding more integrations in the future?

Yes! We are adding support for Jira, Linear and GitHub this month, and have more on the roadmap. We’re also aiming to support new sources for knowledge base ingestion like Notion.

Can I use RunSybil through an API?

Yes! You can add applications, launch tests and receive findings through our API along with other functionalities.

Does RunSybil do continuous testing?

Yes, users can perform “change tests” where the agents do testing relative to a specific commit or commits. Additionally, users can schedule recurring tests on a time basis.