Dockerized AI-powered web scraper using Playwright with virtual display and vision-based captcha solving, no third-party captcha services needed.

Do not run this image blindly. Key things to check before installing or executing: - Ask for the missing Dockerfile and inspect it: the registry files reference a Dockerfile but none is provided — do not build or run a container from an unknown Dockerfile or from untrusted sources. - Understand where screenshots and page data are sent: the code delegates to AgentBrowser.execute which will call an external model service; confirm which endpoints are used and whether you control the API key. Treat page screenshots as sensitive (they may contain credentials or PII). - Avoid handing over sensitive .env values: the run examples mount an .env into the container. Do not place secrets (AWS, DB, SSH keys, etc.) into .env that is passed to untrusted containers. - Harden VNC: the examples expose port 5900 with no password. If you must run, bind VNC only to an isolated network, require authentication, or avoid exposing it to host network. - Consider offline/air-gapped testing: run the container in an isolated network or VM without network access to verify behavior before exposing it to the internet or production data. - If you need the capability, prefer a vetted implementation: request the missing Dockerfile, a signed release, and clear documentation about which LLM endpoints are used and how long data is retained. If the skill will see login pages, do not provide real credentials during testing. Given the inconsistencies and potential for sensitive data leakage, treat this skill as suspicious and require additional transparency and controls before using it with real data or secrets.

Type: OpenClaw Skill Name: agent-vision-scraper Version: 1.0.0 The skill is classified as suspicious due to two primary security vulnerabilities: 1) The `skill.md` and `README.md` explicitly state that VNC access is enabled on port 5900 without a password, allowing anyone with network access to view and potentially control the browser session, which could expose sensitive data. 2) The `agent-scraper.js` script directly embeds the user-provided instruction (`userInstruction`) into the LLM's prompt (`augmentedInstruction`), creating a significant prompt injection vulnerability. While the skill's stated purpose is legitimate web scraping, these flaws could be exploited by a malicious user or external attacker to compromise data or control the agent.