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