voice-dna-creator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of user-provided writing samples (e.g., newsletters, blog posts, social media).
- Ingestion points: User-provided text samples or files within the knowledge folder as described in Step 1 of the analysis process.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the content being analyzed.
- Capability inventory: The skill is restricted to text synthesis and writing a JSON file to the
/context/directory. No network operations, system command executions, or dynamic code evaluations were identified. - Sanitization: No explicit sanitization or filtering of the ingested content is mentioned in the analysis steps.
Audit Metadata