script-to-tts

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's functionality is limited to reading script files and writing reformatted versions to specific subdirectories within the workspace. No high-risk operations such as arbitrary command execution, network exfiltration, or credential access were detected.
  • [PROMPT_INJECTION]: The skill ingests untrusted text from script files (scripts/final/script.md), creating an indirect prompt injection surface. However, the risk is minimized by the skill's specific instructions to perform text normalization and stripping of non-dialogue content.
  • Ingestion points: scripts/final/script.md and user-provided script paths.
  • Boundary markers: No explicit delimiters are used to wrap the input content.
  • Capability inventory: File system read and write operations limited to local project directories.
  • Sanitization: The skill explicitly strips bracketed visual directions and normalizes text, which acts as a form of content sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:27 PM
Security Audit — agent-trust-hub — script-to-tts