skyrim-voiced-dialogue
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external data from the user's mod library, including ESM, ESP, DLL files, scripts, and logs.
- Ingestion points: Project files (ENVIRONMENT.md, TASK.md) and mod library assets (ESM, ESP, DLL, script, log, archive).
- Boundary markers: No specific delimiters or safety warnings for embedded instructions are provided.
- Capability inventory: Voice and lip-sync asset generation, plugin authoring, and script modding.
- Sanitization: No explicit sanitization or filtering of external content is documented.
- [DYNAMIC_EXECUTION]: The skill references the use of bundled PowerShell and Python 3 scripts for generating dialogue assets and performing modding tasks.
- Execution patterns: Relies on external scripts for WAV/XWM/FUZ/LIP generation and plugin authoring workflows.
Audit Metadata