alterlab-genai-voice-designer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting data from external sources such as web search results and user-provided project files, which constitutes a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill is instructed to 'search the web' for platform updates and 'read existing project files' (scripts, brand guidelines) for context.
- Boundary markers: No specific delimiters or instructions to disregard embedded commands in external data are provided.
- Capability inventory: The skill utilizes web search capabilities and file system access for reading and writing production guides (e.g., writing to
{project}-voice-identity.md). - Sanitization: The instructions do not include validation or sanitization steps for data retrieved from web searches or local files.
Audit Metadata