voice-checker

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted text data from lyrics and prose files provided via user arguments, which creates a surface for indirect prompt injection where instructions embedded in the data could attempt to influence the generated report.
  • Ingestion points: Reads files from paths specified in $ARGUMENTS, including track files, README.md, and promo documents.
  • Boundary markers: The instructions do not define delimiters or provide specific warnings to the agent to ignore instructions embedded in the content being reviewed.
  • Capability inventory: The skill is restricted to Read, Glob, and Grep tools; it lacks network access, file-writing capabilities, or tools for arbitrary code execution.
  • Sanitization: No sanitization, validation, or filtering of the processed text content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 11:27 PM