The Agent Skills Directory

[COMMAND_EXECUTION]: The script audit.py executes system-level commands using subprocess.run. It specifically invokes docker exec to perform database queries and curl to fetch data from the WordPress REST API.
[CREDENTIALS_UNSAFE]: The script audit.py contains hardcoded database credentials (DB_USER="wordpress", DB_PASS="wordpress") used to access the WordPress database container.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection and data-driven attacks through the processing of untrusted external data.
Ingestion points: Data is fetched from potentially untrusted WordPress REST API endpoints in audit.py (functions get_all_pages and get_all_posts).
Boundary markers: No delimiters or instructions are used to separate untrusted API data from the agent's logic.
Capability inventory: The skill possesses the ability to execute shell commands (docker, curl) and perform raw SQL queries.
Sanitization: The script lacks sanitization for fields like post_id before they are interpolated into SQL strings in get_yoast_meta and get_media_info, creating a SQL injection surface if the API response is compromised.

seo-optimizer