The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill utilizes the execute tool to run JavaScript code generated by the agent. This code handles complex logic such as batching identifiers, branching based on tool responses, and implementing post-enrichment verification logic. This behavior is a standard implementation detail for Crustdata's Code Mode functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from the web to resolve identities, which introduces a surface for indirect prompt injection.\n
Ingestion points: External data is ingested via web_search_live (search snippets) and web_enrich_live (web page and GitHub commit content) into the agent's reasoning loop.\n
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the processing logic for these external inputs.\n
Capability inventory: The skill possesses the capability to execute scripts (execute), perform network API calls (callTool), and save state to local files (progress.json).\n
Sanitization: There is no explicit sanitization or validation of the retrieved web content beyond business logic verification (e.g., name similarity checks).\n- [COMMAND_EXECUTION]: The skill operates within a script execution environment to coordinate its multi-phase waterfall enrichment process.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves data from the vendor's API infrastructure (crustdata.com) and well-known professional and developer platforms like LinkedIn and GitHub to populate contact profiles.

email-enrichment