The Agent Skills Directory

[SAFE]: The skill provides a transparent and standard workflow for prospecting and lead qualification that matches its stated purpose. It utilizes internal tools specifically designed for searching and analyzing business data.
[NO_CODE]: The skill is composed entirely of instructional content in markdown format. It does not bundle or attempt to execute any scripts, binaries, or other code components, which inherently reduces its risk profile.
[EXTERNAL_DOWNLOADS]: The skill references enrichment tools that interact with well-known and professional services such as LinkedIn and company databases. These data-fetching operations are necessary for the tool's prospecting functions and do not originate from untrusted or suspicious sources.
[PROMPT_INJECTION]: The skill processes data from external sources (e.g., company descriptions and person biographies), which introduces a theoretical surface for indirect prompt injection. * Ingestion points: External information enters the agent context via the enrich_person, enrich_company, and find_person tool outputs. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data from external tool outputs as untrusted content. * Capability inventory: The available capabilities are limited to specified search, qualification, and enrichment tools within the defined environment. * Sanitization: The instructions do not specify any validation or sanitization steps for data returned from external enrichment tools before processing.

prospector