The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts campaign-tracker.py and scripts/keyword-clusterer.py to manage keyword data and campaigns.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from user-supplied URLs to extract keyword themes.
Ingestion points: User-provided seed keywords, topics, and URLs for keyword theme extraction (SKILL.md).
Boundary markers: No markers or delimiters are defined to isolate external data from the agent's internal instructions.
Capability inventory: The skill has the ability to execute shell commands via Python and read local configuration files from the user's home directory.
Sanitization: The instructions do not specify any sanitization or validation of content retrieved from external sources before processing.

keyword-research