customer-health-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze data from untrusted external sources, including CRM notes, support ticket transcripts, and social media sentiment. There are no instructions for implementing boundary markers or sanitizing this data before processing, creating a potential surface for indirect prompt injection if the agent executes these analytical tasks on malicious input. * Ingestion points: Customer data sources defined in rules/data-enrichment-360.md and rules/indicators-leading-lagging.md (CRM, Support tickets, Social signals, News APIs). * Boundary markers: Absent from all instructions. * Capability inventory: The skill consists of documentation and does not include executable scripts. * Sanitization: No sanitization or validation logic is specified for external data inputs.
Audit Metadata