The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the infsh CLI tool within a Bash environment to execute keyword research, search intent analysis, and competitor data extraction.
[EXTERNAL_DOWNLOADS]: The skill documentation references external installation guides on GitHub and suggests adding additional modules from the inference-sh organization using the npx package runner.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external websites. 1. Ingestion points: Data enters the agent context through the search and extraction capabilities of the tavily and exa tools (SKILL.md). 2. Boundary markers: No specific delimiters or instructions are provided to the agent to disregard instructions found within the retrieved external content. 3. Capability inventory: The skill leverages the infsh platform to run various search-related applications and generate images from HTML. 4. Sanitization: No mechanisms for filtering or sanitizing content retrieved from third-party URLs are specified.

seo-content-brief