prospecting
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process data from external, untrusted sources such as prospect websites and third-party APIs. Ingestion points: Website content extracted via Firecrawl or Browserbase (references/local-prospecting.md); data enriched through tools like Apollo, Clay, and ZoomInfo (SKILL.md). Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the ingested data. Capability inventory: The skill can execute local scripts (node tools/clis/github-prospects.js) and interact with various sales tools and CRM integrations (SKILL.md). Sanitization: No explicit sanitization or validation of external content is described.
- [COMMAND_EXECUTION]: The skill instructions include the execution of a local utility script using the Node.js runtime to process developer-intent signals. Evidence:
node tools/clis/github-prospects.js stargazers <owner/repo> --enrich --with-company --format csvin references/saas-prospecting.md.
Audit Metadata