The Agent Skills Directory

[COMMAND_EXECUTION]: The orchestrator script scripts/auto_implementer.py uses subprocess.run to execute other Python scripts within the skill's directory (e.g., audit_report.py, content_optimizer.py). While this is used for internal orchestration, it represents a local execution surface.
[EXTERNAL_DOWNLOADS]: The script scripts/indexnow_submit.py performs network operations using urllib.request.urlopen to submit URLs to search engine indexing endpoints such as Bing and Yandex. These are well-known services and part of the skill's primary functionality for Generative Engine Optimization (GEO).
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting and parsing untrusted data from user-provided content files.
Ingestion points: scripts/analyze_content.py and scripts/keyword_analyzer.py read and process local HTML, Markdown, and JSX files.
Boundary markers: The scripts use standard HTML/Markdown parsing and regular expressions to extract specific tags, but do not implement explicit instructions to ignore embedded AI commands within the content.
Capability inventory: The skill possesses capabilities for shell command execution (via subprocess orchestration in auto_implementer.py) and network communication (via indexnow_submit.py).
Sanitization: Basic text cleaning and HTML tag removal are performed during processing.

seo-geo-optimizer