The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted user data via its analysis scripts, which creates a potential surface for injection attacks where hidden instructions in the input text could influence the agent's behavior.
Ingestion points: scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py are designed to read content from user-specified files (e.g., existing_content.txt, blog_post.md) for processing.
Boundary markers: Absent. The scripts do not use delimiters or include instructions for the agent to disregard potential instructions embedded within the content being analyzed.
Capability inventory: The provided Python scripts are limited to text analysis and readability scoring; they do not utilize dangerous capabilities such as network operations, file writing, or subprocess execution.
Sanitization: Absent. The scripts perform direct text analysis without filtering for instructional keywords or escaping patterns.

content-creator