The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to run Python scripts scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py for text processing.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided text files, which could contain hidden instructions that might influence the agent. \n * Ingestion points: File reading within scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py. \n * Boundary markers: Absent. No delimiters are used to wrap the untrusted content being analyzed. \n * Capability inventory: Local file reading (restricted to the workspace) and execution of local Python scripts. \n * Sanitization: Path resolution in safe_user_path prevents traversal attacks, but file content is not sanitized for natural language instructions.

content-creator