The Agent Skills Directory

[SAFE]: The skill utilizes local Python scripts (brand_voice_analyzer.py and seo_optimizer.py) to perform text analysis for brand voice consistency and SEO metrics. These scripts use only standard Python libraries and do not perform any network operations, external downloads, or unauthorized file system modifications.
[INDIRECT_PROMPT_INJECTION]: The skill contains a surface for processing untrusted data as it is designed to analyze user-provided text files.
Ingestion points: scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py ingest content from local file paths provided via command-line arguments.
Boundary markers: Absent, as the scripts perform programmatic text analysis rather than passing the raw content to an LLM for instruction following.
Capability inventory: The analysis scripts are limited to regex-based counting and scoring; they lack capabilities for subprocess execution, network requests, or file writing.
Sanitization: Not present, but the risk is mitigated by the limited scope of the scripts' operations which do not treat input as code or instructions.

content-creator