voc-synthesis
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data such as customer call transcripts, survey responses, and review mining which could theoretically contain prompt injection attacks.
- Ingestion points: Raw VOC data processed in 'Act 1 — Ingest & Code'.
- Boundary markers: None explicitly defined in the instructions to separate data from system prompts.
- Capability inventory: The skill is restricted to text synthesis and markdown report generation. It does not utilize shell execution, file-writing tools, or network operations.
- Sanitization: There are no explicit sanitization or filtering steps for the ingested customer language.
Audit Metadata