prospecting

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local utility script via node tools/clis/github-prospects.js to process GitHub repository engagement data (stargazers and forks) for developer-focused prospecting.
  • [EXTERNAL_DOWNLOADS]: The workflow integrates several well-known and reputable third-party services including Apollo, ZoomInfo, Clay, and Truelist for firmographic enrichment, intent tracking, and email deliverability verification.
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface as it is designed to ingest and process content from external prospect websites using Firecrawl and Browserbase.
  • Ingestion points: Untrusted external business websites accessed via Firecrawl or Browserbase (noted in references/data-sources.md).
  • Boundary markers: No specific boundary markers are defined in the instructions to separate ingested web content from the agent's core instructions.
  • Capability inventory: The skill possesses the capability to execute local commands (node), perform network API requests to various providers, and write data to local files (CSV output).
  • Sanitization: The instructions do not specify any sanitization or validation logic for data extracted from external websites.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:51 PM