claude-video-screenshot

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool to perform setup tasks and run automation scripts like scripts/web_capture.py. These operations are consistent with the skill's purpose for web interaction and video processing.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the playwright library and its associated browser binaries. Playwright is a well-known, industry-standard tool for browser automation from a reputable source.
  • [PROMPT_INJECTION]: The skill accepts untrusted inputs such as URLs and CSS selectors which are passed to Playwright. While this is necessary for functionality, it represents an attack surface for indirect prompt injection if the browser processes malicious content or if the resulting images are subsequently analyzed by the AI without security boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:55 PM
Security Audit — agent-trust-hub — claude-video-screenshot