The Agent Skills Directory

[SAFE]: No malicious patterns, command execution, or data exfiltration attempts were detected. The skill contains only high-level instructions and methodology for debugging browser interactions.
[NO_CODE]: The skill does not include any scripts, dependencies, or configuration files that trigger code execution.
[INDIRECT_PROMPT_INJECTION]: The skill outlines a process for interacting with external web content (DOM, console logs, network traffic). This is a known attack surface for indirect prompt injection, as malicious websites could attempt to influence the agent. However, the skill's instructions prioritize evidence gathering and root-cause analysis rather than granting the agent unsafe autonomous capabilities.

browser-debugger