Commit Graph

81 Commits

Author SHA1 Message Date
ahmed
a90082bc53 feat(prompts): enhance Next.js framework module with reconnaissance techniques
- Add route enumeration section with __BUILD_MANIFEST.sortedPages technique
  - Add environment variable leakage detection (NEXT_PUBLIC_ prefix)
  - Add data fetching over-exposure section for __NEXT_DATA__ inspection
  - Add API route path normalization bypass techniques
2026-01-02 15:35:52 -08:00
Vincent550102
6fc592b4e8 fix: Convert dictionary views to lists for stable iteration over agents and tool executions. 2026-01-02 14:17:32 -08:00
Vincent550102
62cca3f149 fix: convert tool_executions.items() to list for stable iteration 2026-01-02 14:17:32 -08:00
0xallam
78b6c26652 enhance todo tool prompt 2025-12-15 10:26:59 -08:00
0xallam
eb0c52b720 feat: add PyInstaller build for standalone binary distribution
- Add PyInstaller spec file and build script for creating standalone executables
- Add install.sh for curl | sh installation from GitHub releases
- Add GitHub Actions workflow for multi-platform builds (macOS, Linux, Windows)
- Move sandbox-only deps (playwright, ipython, libtmux, etc.) to optional extras
- Make google-cloud-aiplatform optional ([vertex] extra) to reduce binary size
- Use lazy imports in tool actions to avoid loading sandbox deps at startup
- Add -v/--version flag to CLI
- Add website and Discord links to completion message
- Binary size: ~97MB (down from ~120MB with all deps)
2025-12-15 08:21:03 -08:00
0xallam
2899021a21 chore(todo): encourage batched todo operations
Strengthen schema guidance to batch todo creation, status updates, and completions while reducing unnecessary list refreshes to cut tool-call volume.
2025-12-15 07:41:33 -08:00
0xallam
dcf77b31fc chore(tools): raise sandbox execution timeout
Increase default sandbox tool execution timeout from 120s to 500s while keeping connect timeout unchanged.
2025-12-14 20:40:00 -08:00
0xallam
37c8cffbe3 feat(tools): add bulk operations support to todo tools
- update_todo: add `updates` param for bulk updates in one call
- mark_todo_done: add `todo_ids` param to mark multiple todos done
- mark_todo_pending: add `todo_ids` param to mark multiple pending
- delete_todo: add `todo_ids` param to delete multiple todos
- Increase todo renderer display limit from 10 to 25
- Maintains backward compatibility with single-ID usage
- Update prompts to keep todos short-horizon and dynamic
2025-12-14 20:31:33 -08:00
0xallam
c29f13fd69 feat: add --scan-mode CLI option with quick/standard/deep modes
Introduces scan mode selection to control testing depth and methodology:
- quick: optimized for CI/CD, focuses on recent changes and high-impact vulns
- standard: balanced coverage with systematic methodology
- deep: exhaustive testing with hierarchical agent swarm (now default)

Each mode has dedicated prompt modules with detailed pentesting guidelines
covering reconnaissance, mapping, business logic analysis, exploitation,
and vulnerability chaining strategies.

Closes #152
2025-12-14 19:13:08 -08:00
Rohit Martires
5c995628bf Feat: added support for non vision models STRIX_DISABLE_BROWSER flag (#188)
Co-authored-by: 0xallam <ahmed39652003@gmail.com>
2025-12-14 23:45:43 +04:00
Ahmed Allam
624f1ed77f feat(tui): add markdown rendering for agent messages (#197)
Add AgentMessageRenderer to render agent messages with basic markdown support:
- Headers (#, ##, ###, ####)
- Bold (**text**) and italic (*text*)
- Inline code and fenced code blocks
- Links [text](url) and strikethrough

Update system prompt to allow agents to use simple markdown formatting.
2025-12-14 22:53:07 +04:00
Ahmed Allam
2b926c733b feat(tools): add dedicated todo tool for agent task tracking (#196)
- Add new todo tool with create, list, update, mark_done, mark_pending, delete actions
- Each subagent has isolated todo storage keyed by agent_id
- Support bulk todo creation via JSON array or bullet list
- Add TUI renderers for all todo actions with status markers
- Update notes tool to remove priority and todo-related functionality
- Add task tracking guidance to StrixAgent system prompt
- Fix instruction file error handling in CLI
2025-12-14 22:16:02 +04:00
Ahmed Allam
a075ea1a0a feat(tui): add syntax highlighting for tool renderers (#195)
Add Pygments-based syntax highlighting with native hacker theme:
- Python renderer: Python code highlighting
- Browser renderer: JavaScript code highlighting
- Terminal renderer: Bash command highlighting
- File edit renderer: Auto-detect language from file extension, diff-style display
2025-12-14 04:39:28 +04:00
Alexander De Battista Kvamme
9fedcf1551 Fix/ Long text instruction causes crash (#184) 2025-12-08 23:23:51 +04:00
0xallam
1edd8eda01 fix: lint errors and code style improvements 2025-12-07 17:54:32 +02:00
0xallam
bd8d927f34 fix: add timeout to sandbox tool execution HTTP calls
Replace timeout=None with configurable timeouts (120s execution, 10s connect)
to prevent hung sandbox connections from blocking indefinitely.

Configurable via STRIX_SANDBOX_EXECUTION_TIMEOUT and STRIX_SANDBOX_CONNECT_TIMEOUT
environment variables.
2025-12-07 17:07:25 +04:00
0xallam
37c9b4b0e0 fix: make LLM_API_KEY optional for all providers
Some providers like Vertex AI, AWS Bedrock, and local models don't
require an API key as they use different authentication mechanisms.
2025-12-07 02:07:28 +02:00
0xallam
208b31a570 fix: filter out image_url content for non-vision models 2025-12-07 02:13:02 +04:00
0xallam
4297c8f6e4 fix: pass api_key directly to litellm completion calls 2025-12-07 01:38:21 +04:00
0xallam
286d53384a fix: set LITELLM_API_KEY env var for unified API key support 2025-12-07 01:38:21 +04:00
0xallam
ab40dbc33a fix: improve request queue reliability and reduce stuck requests 2025-12-06 20:44:48 +02:00
Vincent Yang
c97ff94617 feat: Show Model Name in Live Stats Panel (#169)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2025-12-03 18:45:01 +00:00
Alexander De Battista Kvamme
c0e547928e Real-time display panel for agent stats (#134)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2025-11-25 12:06:20 +00:00
Trusthoodies
78d0148d58 Add open redirect, subdomain takeover, and info disclosure prompt modules (#132)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2025-11-25 10:32:55 +00:00
Ahmed Allam
a11cd09a93 feat: support file-based instructions for detailed test configuration 2025-11-23 00:46:37 +04:00
Ahmed Allam
68ebdb2b6d feat: enhance run name generation to include target information 2025-11-22 22:54:07 +04:00
Ahmed Allam
5befb32318 feat: implement incremental pentest data persistence 2025-11-22 22:54:07 +04:00
cyberseall
86e6ed49bb feat(llm): make LLM request queue rate limits configurable and more conservative
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2025-11-22 17:07:43 +00:00
Ahmed Allam
383d53c7a9 feat(agent): implement agent identity guidline and improve system prompt 2025-11-15 16:21:05 +04:00
Ahmed Allam
478bf5d4d3 refactor(llm): remove unused temperature parameter from LLMConfig 2025-11-15 12:44:40 +04:00
Ahmed Allam
d1f7741965 feat(llm): enhance model features handling with pattern matching 2025-11-15 12:43:43 +04:00
Ahmed Allam
821929cd3e fix(agent): increase waiting time threshold from 120 to 600 seconds 2025-11-15 12:39:46 +04:00
Ahmed Allam
dab69af033 fix(runtime): correct DOCKER_HOST parsing for sandbox URL 2025-11-14 02:41:00 +04:00
Ahmed Allam
6abb53dc02 feat: support scanning IP addresses 2025-11-14 01:38:58 +04:00
Ahmed Allam
1abfb360e4 feat: add configurable timeout for LLM requests 2025-11-12 18:58:03 +04:00
Ahmed Allam
6a84ea94fa feat: add error handling for headless mode in agent execution and improve CLI on scan failures 2025-11-01 03:29:44 +02:00
Ahmed Allam
cf1d43706a feat: improve completion message display for scan results and user interruptions 2025-11-01 03:02:47 +02:00
Ahmed Allam
b9f8ee3f67 fix: replace raise with sys.exit(1) in clone_repository for better error handling 2025-11-01 02:38:37 +02:00
Ahmed Allam
2d6db8f95e feat: enhance agent prompt for multi-target testing 2025-11-01 02:38:37 +02:00
Ahmed Allam
738fdc2d49 feat: implement multi-target scanning 2025-11-01 02:38:37 +02:00
Ahmed Allam
395013fdeb feat(docs): Enhance README with headless mode and CI/CD integration examples 2025-10-31 21:07:21 +02:00
Ahmed Allam
ecf5271981 feat: Add iteration limit warnings for agent 2025-10-31 21:07:21 +02:00
Ahmed Allam
71c232b577 feat: Increase agents max_iterations to 300 2025-10-31 21:07:21 +02:00
Ahmed Allam
f2b4eccc5b refactor: Migrate tracer to new telemetry module 2025-10-31 21:07:21 +02:00
Ahmed Allam
86dd6f5330 feat(interface): Introduce non-interactive CLI mode and restructure UI layer 2025-10-31 21:07:21 +02:00
Ahmed Allam
54851e2e0a feat(cli): per‑severity vuln counts in test completion panel 2025-10-28 22:48:52 -07:00
Ahmed Allam
a4712b7b78 chore: Bump version to 0.1.19 and enhance splash screen 2025-10-29 02:15:30 +03:00
Ahmed Allam
96f5c44799 refactor: Update agent instructions and descriptions 2025-10-28 13:17:46 -07:00
Ahmed Allam
49df6ef8e0 feat: Implement waiting timeout handling in BaseAgent and AgentState 2025-10-28 13:17:46 -07:00
Ahmed Allam
c78f7d37de chore: remove unneeded gitkeep files 2025-10-18 18:39:39 -07:00