real-estate-post-sale-referral-engine
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's code and instructions are consistent with its stated purpose. No malicious patterns, such as command execution, data exfiltration, or obfuscation, were found in the skill files.
- [INDIRECT_PROMPT_INJECTION]: The skill manages client-supplied data, presenting a potential surface for indirect prompt injection.
- Ingestion points: Personal data such as client names, occupations, and family details are ingested into the agent's context in
SKILL.mdto populate 'Client Relationship Cards'. - Boundary markers: The skill uses Markdown structures like headers and tables to organize data, but it does not employ explicit security delimiters or 'ignore' instructions for the ingested content.
- Capability inventory: The skill is limited to text generation, report creation, and relationship tracking; it does not request access to dangerous tools, network operations, or shell execution.
- Sanitization: No validation or sanitization procedures for external strings are defined in the instructions.
Audit Metadata