The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks detected.
Educational Content: The SKILL.md file contains standard search engine optimization guidelines (E-E-A-T, Core Web Vitals) and does not contain prompt injection or deceptive instructions.
Script Analysis: The scripts/seo_checker.py script is a straightforward auditing tool.
File Access: It uses pathlib to find and read local HTML, JSX, and TSX files based on a user-provided directory. It restricts its search to 50 files and excludes common system and dependency directories (e.g., node_modules, .git).
Network/RCE: The script does not use network libraries or perform any remote code execution.
Command Execution: No dangerous system calls or shell commands are invoked.
Data Handling: It only reports filenames and static issue descriptions (e.g., "Missing tag"). It does not exfiltrate data or handle sensitive credentials.
[Indirect Prompt Injection] (SAFE): While the script reads external files (HTML/JSX), the risk of indirect prompt injection is negligible because it does not echo the untrusted content back to the agent; it only checks for the presence or absence of specific tags using regex.

seo-fundamentals