skills/rhuss/cc-prose/voice-extractor/Gen Agent Trust Hub

voice-extractor

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses the Read and Glob tools to ingest content from external documents for style analysis. It does not implement boundary markers or instructions to disregard embedded commands, making it susceptible to indirect prompt injection.
  • Ingestion points: Files accessed through Read and Glob tools (referenced in SKILL.md).
  • Boundary markers: Not specified for processed content.
  • Capability inventory: Read, Write, Glob, and AskUserQuestion tools.
  • Sanitization: Not performed on the input text corpus.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 03:50 AM