lead-qualification

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core functionality of processing untrusted lead data from external sources.\n
  • Ingestion points: Lead data is ingested from CSV files, Google Sheets, and LinkedIn profile data retrieved via the Apify API in scripts/enrich_leads.py.\n
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used to separate lead data from the evaluation instructions in the subagent prompts.\n
  • Capability inventory: The skill can execute local Python scripts, perform web searches, and write results to the local filesystem and external Google Sheets.\n
  • Sanitization: No explicit sanitization or validation of the lead content is performed before the data is processed by the scoring subagents.\n- [COMMAND_EXECUTION]: The skill executes a bundled Python script, scripts/enrich_leads.py, to manage batch lead enrichment. This execution is limited to the skill's own internal logic and is used for its primary stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 11:42 AM