voice-injection-rewriter
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves ingesting and transforming arbitrary user-provided text ('AI Input') and voice samples. This creates a surface for indirect prompt injection, as malicious instructions hidden within the input content could potentially attempt to influence the agent's behavior or override its instructions during the rewriting process.
Audit Metadata