The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from external websites and search results.
Ingestion points: Data is retrieved from logo alt-text, headings, and technology directories using the scrape_website_logos.py, scrape_wayback_logos.py, and search_builtwith.py scripts.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the scraped strings.
Capability inventory: The skill creates directories, writes files, and executes local scripts.
Sanitization: A clean_name function filters for length and noise but does not perform comprehensive sanitization for injection patterns.
[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts and shell commands (mkdir) as part of its standard research and reporting workflow.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the requests library from the official Python package index, which is standard for network operations.

customer-discovery