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
Make the root agent follow up open coverage rows before finishing (#1573)
14cc948 alex s committed 27 days ago
Bump aiohttp, graphql-core, vite and trufflehog past known CVEs (#1569)
5943988 alex s committed 27 days ago
feat(skills): expand XSS coverage for HTML injection and normalization (#1559)
0f81f40 theo-at-strix committed 28 days ago
build(deps): enforce a 5-day release cooldown for uv and npm resolution (#1556)
a3c3123 alex s committed 29 days ago
fix(reporting): keep HTTP exchange evidence when the proxy is slow to verify ids (#1551)
fde37a1 alex s committed 29 days ago
fix(llm): keep request_log.install(); record tool call timings; both only with STRIX_RUN_RECORD_TIMINGS
aa2036f Ian committed 1 month ago
feat(llm): run.json records every provider request's timing, provider and tokens in llm_requests
f4a7413 Ian committed 1 month ago
fix(core): a parked agent keeps its pause reason and drains queued messages on resume
a0f8ea2 Ahmed Allam committed 1 month ago
fix(core): an operator pause holds under every budget policy and only resume_budget lifts it
6bd1cea Ahmed Allam committed 1 month ago
fix(agents): the running-process marker is matched only in the result header, never in command output
ee22e2b Ahmed Allam committed 1 month ago
fix(agents): the non-TTY note goes into the Output section so renderers keep stripping the metadata block
2b98deb Ahmed Allam committed 1 month ago
fix(agents): exec_command states the 30 s yield cap and that a running non-TTY process cannot be polled
5e9e69a Ahmed Allam committed 1 month ago
feat(llm): extra request-body fields via LLM_EXTRA_BODY (#1495)
972f509 Szymon Nastaly committed 1 month ago
fix(models): replay malformed tool-call arguments as valid JSON (#1327)
ca20626 alex s committed 1 month ago
test(resume-picker): put the pty in cbreak so the key-reader test can't hang on macOS (#1527)
e21f9ce ian-at-strix committed 1 month ago
fix(reporting): drop the static-analysis disclaimer from dependency evidence (#1520)
87f2d78 yoni-at-strix committed 1 month ago
feat(runtime): accept an awaitable extra_files in create_or_reuse so the sandbox create does not wait for it
956a267 Ahmed Allam committed 1 month ago
fix(runtime): keep the default path blocking on the proxy endpoint and discard a sandbox created after a cancelled deferred bring-up
0f8db1f Ahmed Allam committed 1 month ago
feat(runtime): defer the sandbox bring-up behind a DeferredSandboxSession when create_or_reuse is called with defer=True
4bf7541 Ahmed Allam committed 1 month ago
fix(tui): give the targets box only rows the agents panel would get, and always count hidden targets
442b3c3 Ian committed 1 month ago
feat(tui): move the run's targets into their own sidebar box under the viewer
710fe7b Ian committed 1 month ago
feat(reporting): accept code_locations on dependency reports (#1366)
429f621 yoni-at-strix committed 1 month ago
feat(agents): let callers choose the top-level agent's finish tool (#1496)
62b4964 ian-at-strix committed 1 month ago
fix(mcp): load catalogs before agents discover connections (#1492)
f5a9004 alex s committed 1 month ago
feat(llm): bound the first stream event and the whole stream (#1487)
4695290 ian-at-strix committed 1 month ago