prospecting
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as prospect websites and social platforms through tools like Firecrawl or Browserbase. While it includes instructions to verify evidence, the ingestion of unverified external content presents a surface for indirect prompt injection.
- [COMMAND_EXECUTION]: The skill references the execution of a local Node.js utility to process GitHub data for developer-focused prospecting. This represents standard functional behavior for the described task.
- [EXTERNAL_DOWNLOADS]: The skill suggests using various external data providers and enrichment services like Apollo, ZoomInfo, and Crunchbase. These are well-known business services and their use is consistent with the skill's primary purpose.
Audit Metadata