The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local command-line tools and Python scripts to perform its functions. Specifically, it uses grep for guideline checking and executes scripts/brand_voice_analyzer.py and scripts/seo_optimizer.py to process text content.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted text from external files (e.g., blog posts or existing brand content).
Ingestion points: Text content is read from user-provided files such as existing_content.txt and blog_post.md via script arguments and shell commands.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when the agent reads or processes these files.
Capability inventory: The skill allows the agent to execute Python scripts, read local files, and create new files using cp.
Sanitization: The included Python scripts perform statistical and keyword analysis using regular expressions but do not filter for or sanitize potential prompt injection strings within the input content.

content-creator