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
Stabilize agent-browser launch and screenshot routing
0xallamc88b2bbb9979
diff --git a/containers/Dockerfile b/containers/Dockerfileindex 62495282..51d57532 100644--- a/containers/Dockerfile+++ b/containers/Dockerfile@@ -88,10 +88,10 @@ RUN npm install -g retire@latest && \npm install -g tree-sitter-cli@latest && \npm install -g [email protected]-USER pentesterENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromiumENV AGENT_BROWSER_USER_AGENT="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"-ENV AGENT_BROWSER_ARGS="--disable-blink-features=AutomationControlled --exclude-switches=enable-automation --disable-features=IsolateOrigins,site-per-process,Translate,BlinkGenPropertyTrees --no-first-run --no-default-browser-check --window-size=1920,1080 --lang=en-US,en --disable-infobars --disable-notifications --disable-save-password-bubble --disable-session-crashed-bubble"+ENV AGENT_BROWSER_ARGS="--disable-blink-features=AutomationControlled,--no-first-run,--no-default-browser-check,--lang=en-US"+ENV AGENT_BROWSER_SCREENSHOT_DIR=/workspace/.agent-browser-screenshotsRUN /home/pentester/.npm-global/bin/agent-browser doctor --offline --quickRUN set -eux; \diff --git a/containers/docker-entrypoint.sh b/containers/docker-entrypoint.shindex 6824e3b8..f8e179b1 100644--- a/containers/docker-entrypoint.sh+++ b/containers/docker-entrypoint.sh@@ -90,6 +90,8 @@ sudo -u pentester certutil -N -d sql:/home/pentester/.pki/nssdb --empty-passwordsudo -u pentester certutil -A -n "Testing Root CA" -t "C,," -i /app/certs/ca.crt -d sql:/home/pentester/.pki/nssdbecho "✅ CA added to browser trust store"+mkdir -p /workspace/.agent-browser-screenshots+echo "✅ Container ready"cd /workspacediff --git a/docs/advanced/configuration.mdx b/docs/advanced/configuration.mdxindex 4d51f3c6..a40b9fcf 100644--- a/docs/advanced/configuration.mdx+++ b/docs/advanced/configuration.mdx@@ -41,10 +41,6 @@ Configure Strix using environment variables or a config file.API key for Perplexity AI. Enables real-time web search during scans for OSINT and vulnerability research.</ParamField>-<ParamField path="STRIX_DISABLE_BROWSER" default="false" type="boolean">- Disable browser automation tools.-</ParamField>-<ParamField path="STRIX_TELEMETRY" default="1" type="string">Global telemetry default toggle. Set to `0`, `false`, `no`, or `off` to disable both PostHog and OTEL unless overridden by per-channel flags below.</ParamField>diff --git a/strix/skills/tooling/agent_browser.md b/strix/skills/tooling/agent_browser.mdindex 4682adef..9ef810d6 100644--- a/strix/skills/tooling/agent_browser.md+++ b/strix/skills/tooling/agent_browser.md@@ -18,6 +18,10 @@ wired via ``http_proxy`` / ``https_proxy`` env vars — **do not passcaptures all page traffic. Localhost (CDP) traffic is excluded via``NO_PROXY=localhost,127.0.0.1``.+Default viewport is 1280×720. For sites that gate behavior on real+desktop dimensions (responsive breakpoints, bot fingerprinting), run+``agent-browser viewport 1920 1080`` once per session.+## The core loop```bash@@ -37,7 +41,7 @@ next ref interaction.```bash# Take a screenshot of a pageagent-browser open https://example.com-agent-browser screenshot home.png+agent-browser screenshotagent-browser close# Search, click a result, and capture it@@ -48,7 +52,7 @@ agent-browser press Enteragent-browser wait --load networkidleagent-browser snapshot -i # refs now reflect resultsagent-browser click @e5 # click a result-agent-browser screenshot result.png+agent-browser screenshot```The browser stays running across commands so these feel like a single@@ -241,15 +245,22 @@ shell command alone does **not** put the image into your context —chain it with the SDK ``view_image`` tool to actually see it:```bash-exec_command: agent-browser screenshot /workspace/page.png-view_image: {"path": "/workspace/page.png"}+exec_command: agent-browser screenshot+view_image: {"path": "<path printed on stdout>"}```+Default output directory is ``/workspace/.agent-browser-screenshots/``,+which ``view_image`` can read. Prefer the no-arg form (the CLI prints+the full path on stdout — pass that to ``view_image``). If you need a+specific filename, keep it inside that directory or a sibling hidden+dir under ``/workspace``. Never write screenshots to ``/tmp`` —+``view_image`` rejects anything outside the workspace root.+```bash-agent-browser screenshot # temp path, printed on stdout-agent-browser screenshot page.png # specific path (relative to cwd)-agent-browser screenshot --full full.png # full scroll height-agent-browser screenshot --annotate map.png # numbered labels + legend keyed to snapshot refs+agent-browser screenshot # path printed on stdout+agent-browser screenshot /workspace/.agent-browser-screenshots/page.png+agent-browser screenshot --full # full scroll height+agent-browser screenshot --annotate # numbered labels + legend keyed to snapshot refs````--annotate` is designed for multimodal models: each label `[N]` maps@@ -262,6 +273,12 @@ tokens; screenshots cost more. Use `snapshot` first; reach forlayout questions, captchas, custom widgets where the accessibilitytree is incomplete).+If ``view_image`` errors back at you (rejected image, "vision not+supported", or similar), you are running on a text-only model — stop+calling it and stop taking screenshots. Drive the page entirely from+`snapshot -i` refs, `eval` for any DOM/JS state you need to read, and+`text @ref` / `get text` for content extraction.+### Handle multiple pages via tabs```bash