You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Claims are verified against official library documentation via [Context Hub](https://github.com/andrewyng/context-hub) + [Context7](https://context7.com) before any agent asserts framework behavior.
90
94
95
+
<palign="center">
96
+
<imgsrc="docs/images/doc-verify-fix-plan.png"alt="Bug Hunter documentation verification — agents check official library docs via Context Hub and Context7 API before making claims about framework behavior"width="100%">
97
+
</p>
98
+
91
99
<palign="center">
92
100
<imgsrc="docs/images/adversarial-debate.png"alt="Adversarial AI code review debate — Hunter finds bugs, Skeptic challenges with counter-evidence, Referee delivers independent verdict"width="100%">
93
101
</p>
@@ -113,6 +121,10 @@ Claims are verified against official library documentation via [Context Hub](htt
113
121
114
122
Every security finding gets **STRIDE classification**, **CWE ID**, and **CVSS 3.1 scoring** with proof-of-concept payloads.
115
123
124
+
<palign="center">
125
+
<imgsrc="docs/images/security-finding-card.png"alt="Bug Hunter security finding card — bug ID, severity badge, STRIDE and CWE classification, CVSS 3.1 score, reachability rating, and proof of concept payload"width="100%">
0 commit comments