The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes browser automation tools including mcp__playwright__browser_navigate, mcp__playwright__browser_evaluate, and mcp__playwright__browser_click to perform its tasks. These tools are used legitimately for the primary purpose of navigating to and interacting with websites to detect errors.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sourced from external websites, specifically console logs and network request metadata.
Ingestion points: External data enters the agent context through mcp__playwright__browser_console_messages and mcp__playwright__browser_network_requests tools.
Boundary markers: None identified in the instructions.
Capability inventory: Uses Playwright tools for navigation, interaction, and script evaluation.
Sanitization: No explicit sanitization of website-provided content is mentioned. While this creates an attack surface, the behavior is necessary for the skill's diagnostic function.

console-error-scan