playwright-recording

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The reference.md file contains a utility template that uses child_process.execSync to invoke ffprobe. While the template includes basic shell quoting for the file path, this pattern introduces a command execution surface if the path variable is populated from untrusted sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to automate interaction with external websites, creating an ingestion surface for untrusted content. When combined with the skill's capabilities to write files and execute system commands, this presents a risk if an attacker-controlled webpage attempts to influence agent behavior through embedded instructions.
  • Ingestion points: The skill uses page.goto() to navigate to arbitrary URLs specified in the user's scripts.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded content are provided in the templates.
  • Capability inventory: The skill utilizes file system operations (fs.renameSync, fs.mkdirSync) and system command execution (child_process.execSync).
  • Sanitization: The provided examples do not include sanitization or validation of the web content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM