short-drama-image-prompts
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a document generation utility with a focus on asset consistency for drama production. It does not perform network requests or call external APIs.\n- [SAFE]: The provided Python scripts (image_prompt_check.py, selftest.py) are used for offline validation of data structures. They rely exclusively on Python's standard library and do not exhibit dangerous execution patterns.\n- [SAFE]: A security-conscious check is implemented in the validation logic to detect and reject any prompt specifications containing sensitive vendor fields or credentials, such as API keys or access tokens.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes drama scripts and asset facts as part of its normal workflow, creating a standard surface for indirect prompt injection. However, the risk is assessed as safe as the skill lacks network access or shell execution capabilities that could be exploited.\n
- Ingestion points: Data enters from project-specific screenplay indices and asset metadata files.\n
- Boundary markers: The workflow uses strict structural templates and schemas for prompt generation as defined in the provided assets documentation.\n
- Capability inventory: Capabilities are limited to Markdown file generation; no network or shell tools are enabled for the agent in this context.\n
- Sanitization: Validates structure and filters for sensitive credential keys in the data stream using the image_prompt_check.py script.
Audit Metadata