voice-refine

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified. The skill consists entirely of descriptive markdown and examples.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted text data (user dictation).
  • Ingestion points: Raw text input from voice-to-text tools in the transformation pipeline.
  • Boundary markers: None explicitly defined in the instructions to separate data from instructions.
  • Capability inventory: The skill uses the 'Read' tool to access context if files are mentioned in the input.
  • Sanitization: None. The transformation pipeline relies on the agent's internal logic to deduplicate and extract intent, which naturally filters most noise.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM