voice-dissolver
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided text to generate writing style analyses and 'voice anchor cards'.
- Ingestion points: Text input provided by users for analysis in the 'Listen and go' and 'Help me clarify' workflows.
- Boundary markers: The instructions do not define specific delimiters or guidelines for the agent to isolate user-provided content from its own logic.
- Capability inventory: The skill has no access to external tools, file systems, or network resources, limiting its impact to conversational context.
- Sanitization: There is no evidence of input validation or content filtering for the processed text.
Audit Metadata