The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script, scripts/enrich_leads.py, to perform batch LinkedIn profile enrichment. This script is called by the agent to process CSV data and interact with external enrichment APIs.
[INDIRECT_PROMPT_INJECTION]: The lead qualification process ingests and evaluates untrusted data from external sources, creating a vulnerability to prompt injection attacks.
Ingestion points: Data is ingested from user-supplied CSV files, LinkedIn profiles, and Google Sheets, containing unverified text fields like headlines, biographies, and engagement comments.
Boundary markers: The instructions for the parallel qualification subagents do not require the use of explicit delimiters or escaping for the lead data being interpolated into the qualification prompt.
Capability inventory: The agents performing the qualification have access to web search and file system tools. The primary agent context allows for command execution and network operations.
Sanitization: The skill does not implement or require any sanitization, filtering, or validation of the lead data before it is passed to the language model for scoring and reasoning.
[EXTERNAL_DOWNLOADS]: The enrichment script communicates with external API endpoints at api.apify.com and api.gooseworks.ai. Apify is a well-known service for web automation, and Gooseworks AI is the designated vendor of the skill.

lead-qualification