script-to-tts

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs text transformation on local script files. No unauthorized network access, credential exposure, or malicious commands were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via user-supplied scripts. 1. Ingestion points: scripts/final/script.md and brief/tools-and-models.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file system read and write; no shell or network capabilities. 4. Sanitization: The skill removes bracketed text and normalizes numbers/abbreviations for TTS output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:23 PM
Security Audit — agent-trust-hub — script-to-tts