Browser Screenshot Send
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill is coherent and purpose-aligned, but users should remember that it sends browser screenshots through chat channels and may optionally persist them in the workspace.
This skill appears benign and does what it says: it helps agents send browser screenshots to the conversation. Before using it, consider whether the screenshot may contain passwords, account details, private pages, or confidential business data, and make sure the chat channel is an appropriate place to share it.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Screenshots can contain private information from the browser, so sending them to Slack, Discord, Telegram, or similar channels may expose that information to channel participants or logs.
The skill instructs the agent to send screenshot files through the message tool, which may deliver visual page contents to external chat channels.
message action=send media=/root/.openclaw/media/browser/<uuid>.png
Use this skill when screenshot delivery is intended, and avoid capturing or sending pages with sensitive information unless the destination channel is appropriate.
Saved screenshots may remain available in the workspace and could be viewed or reused later.
The skill recommends storing screenshots in the workspace, which can make temporary browser media persist beyond the immediate task.
Recommended: Copy to workspace for persistence: cp <source> /workspace/media/screenshots/<descriptive_name>.png
Only persist screenshots that are needed, use descriptive names, and remove screenshots that contain sensitive information when they are no longer necessary.