Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Python agentsai-hackingai-penetration-testingai-pentestingai-securityartificial-intelligencebug-bountycode-qualityctf-toolscybersecuritycybersecurity-toolsethical-hackinghackingllm-securityoffensive-securitypenetration-testingpentesting-toolsred-teamingsecuritysecurity-automation
Commits on main
fix: Address code review feedback on tool format normalization
b9dcf7f 0xallam committed 9 months ago
fix: Prevent assistant-message prefill rejected by Claude 4.6
e09b5b4 0xallam committed 9 months ago
fix: Handle single-quoted and whitespace-padded tool call tags
e7970de 0xallam committed 9 months ago
fix: Strip quotes from parameter/function names in tool calls
7614fcc 0xallam committed 9 months ago
feat: Normalize alternative tool call formats (invoke/function_calls)
f4d5221 0xallam committed 9 months ago
fix: Strip custom_llm_provider before cost lookup for proxied models
bf8020f 0xallam committed 9 months ago
refactor: Centralize strix model resolution with separate API and capability names
3b3576b 0xallam committed 9 months ago
resolve: merge conflict resolution, llm api base resolution
d2c99ea octovimmer committed 9 months ago
fix: Add rule against duplicating changes across code_locations
30550dd 0xallam committed 9 months ago
fix: Improve code_locations schema for accurate block-level fixes and multi-part suggestions
154040f 0xallam committed 9 months ago
fix: Remove indentation prefix from diff code block markers for syntax highlighting
305ae2f 0xallam committed 9 months ago
feat: Redesign vulnerability reporting with nested XML code locations and CVSS
d6e9b3b 0xallam committed 9 months ago
fix: Polish finish_scan report schema descriptions and examples
0a63ffb 0xallam committed 9 months ago
fix: Replace hardcoded git host detection with HTTP protocol probe
5a76fab 0xallam committed 9 months ago