sales-prospecting

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the orth command-line utility to interact with external APIs (Fiber, Hunter, and Brand.dev). This is used for its primary function of searching for companies, finding prospects, and validating contact information.
  • [DATA_EXPOSURE]: The instructions direct the agent to read from a MEMORY.md file to retrieve context regarding the Ideal Customer Profile (ICP) and current sales pipeline, which is a standard pattern for persistent agent context.
  • [PROMPT_INJECTION]: The workflow involves interpolating natural language descriptions of target customers directly into API search queries. While this is a surface for indirect prompt injection, it is the intended functionality of the natural language search tool and is generally handled by the underlying agent platform's execution constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:54 AM
Security Audit — agent-trust-hub — sales-prospecting