The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to process and analyze external, potentially untrusted content (e.g., existing brand content or blog posts). This creates a surface for indirect prompt injection, where instructions embedded in the analyzed data could attempt to influence the agent's behavior.
Ingestion points: External text files passed to scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py as indicated in SKILL.md.
Boundary markers: The skill's instructions do not currently utilize delimiters or explicit instructions to the agent to ignore embedded commands within the analyzed text.
Capability inventory: The skill performs file reading and executes local Python scripts to process content.
Sanitization: The provided scripts include path validation but do not perform sanitization of the text content itself to detect or neutralize injection patterns.
[COMMAND_EXECUTION]: The skill involves the execution of local Python scripts (brand_voice_analyzer.py and seo_optimizer.py) to analyze content.
Evidence: These scripts utilize a safe_user_path function that resolves file paths and ensures they remain within the current working directory, effectively preventing directory traversal attacks.

content-creator