real-estate-lead-qualification-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted lead data from multiple external sources.\n
- Ingestion points: Raw leads are collected from property portals (Bayut, PropertyFinder, Dubizzle), WhatsApp conversations, and social media platforms as described in the 'Data Ingestion' workflow step in SKILL.md.\n
- Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' warnings for the ingested lead data.\n
- Capability inventory: The agent's core function is to generate detailed scorecards and route prioritized leads to agents, creating an output chain based on untrusted data.\n
- Sanitization: No procedures for input validation, sanitization, or data filtering are specified before processing the incoming lead content.
Audit Metadata