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(cli): apply the --fail-on threshold regardless of run status
45b775d Ahmed Allam committed 1 month ago
fix(tui): link every wrapped line of the viewer URL to the full URL
65172fe Ahmed Allam committed 1 month ago
test: reject a leading heading in any finish_scan example field
0107a15 Ahmed Allam committed 1 month ago
fix(finish_scan): stop asking for a section heading in every report field
c0258b2 Ahmed Allam committed 1 month ago
fix(config): use the Responses API whenever the model's catalog entry lists /v1/responses
99c0711 Ahmed Allam committed 1 month ago
fix(inputs): send reasoning_effort as configured; no route-specific handling
8ab5e39 Ahmed Allam committed 1 month ago
fix(inputs): send reasoning_effort=none explicitly on chat completions; hint at the Responses API when tools+effort are rejected
e1ec259 Ahmed Allam committed 1 month ago
fix(runner): pick the SDK route from the resolved model override
066bd60 Ahmed Allam committed 1 month ago
fix(config): choose Responses vs chat completions from the model, not the base URL
6ab1234 Ahmed Allam committed 1 month ago
fix(reporting): restore create_vulnerability_report parameter descrip… (#1391)
007ed1a alex s committed 1 month ago
chore(models): remove the model quality warning and its allowlists
ef272b8 Ahmed Allam committed 1 month ago
fix(budget): parked agents count as active; park never overwrites a stop
463b149 Ahmed Allam committed 1 month ago
feat(budget): budget_policy=pause parks every agent at the limit until the operator resumes
d355838 Ahmed Allam committed 1 month ago
perf(prompt): load requested skills after a cache point (#1382)
954bc0d ian-at-strix committed 1 month ago
perf(llm): give Claude a cache point before the per-run scope (#1376)
e66c56c ian-at-strix committed 1 month ago
perf(prompt): put per-run scope at the end of the system prompt (#1375)
50425c2 ian-at-strix committed 1 month ago
docs(skills): refresh framework behavior and security testing guidance (#1372)
6ae036e alex s committed 1 month ago