sora
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill uses a bundled CLI tool (scripts/sora.py) to perform all actions. This is the intended and restricted use of system resources.\n- [EXTERNAL_DOWNLOADS] (LOW): The skill dynamically installs the 'openai' package. This is classified as low risk because OpenAI is a verified and trusted provider.\n- [CREDENTIALS_UNSAFE] (SAFE): The skill correctly identifies the need for an API key and instructs the agent to guide the user in setting it as an environment variable, explicitly forbidding its transmission in plain text chat.\n- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted user input into video prompts. Evidence chain: 1. Ingestion points: User input in SKILL.md templates. 2. Boundary markers: Structured key-value prompt formatting. 3. Capability inventory: Execution of local scripts and external API calls. 4. Sanitization: Relies on API-side enforcement and script logic.
Audit Metadata