historical-interview-scripts
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied historical character names and themes which are interpolated into agent prompts. While this presents a common attack surface for indirect injection, the system implements structural boundaries through clear role definitions and structural JSON outputs that mitigate accidental instruction obedience.
- [EXTERNAL_DOWNLOADS]: The project requires standard Python packages from official registries (PyPI) including well-known SDKs for OpenAI, Anthropic, Azure, and Google Cloud, as well as common utilities like Pillow and MoviePy. All referenced external services are well-known technology providers.
- [CREDENTIALS_SAFE]: The system implements secure credential management by instructing users to store sensitive API keys in local configuration files (settings_local.py) or environment variables, avoiding hardcoded secrets in the codebase.
Audit Metadata