voice-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script voice-extractor.ts using the bun runtime to perform transcript analysis. This is the core functionality and uses a path relative to the plugin root.
  • [PROMPT_INJECTION]: The skill processes untrusted text data from transcripts (e.g., WhatsApp, YouTube auto-captions), which introduces a surface for indirect prompt injection.\n
  • Ingestion points: Files like transcript.txt are passed to the voice-extractor.ts script.\n
  • Boundary markers: The workflow does not include instructions to wrap external content in delimiters or use 'ignore' directives.\n
  • Capability inventory: The skill allows the agent to execute shell commands and update author profile metadata.\n
  • Sanitization: Sanitization logic is unknown as the voice-extractor.ts script was not provided in the analyzed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 11:29 AM