story-video-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The orchestrator script scripts/run_story_pipeline.py executes other Python scripts located in sibling directories using subprocess.run. The use of list-based arguments instead of shell strings prevents shell injection attacks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as user-provided themes and file paths, which creates a potential surface for indirect prompt injection if downstream scripts process this data with LLMs without adequate sanitization.
- Ingestion points: Arguments such as --theme, --character, and --script-file in scripts/run_story_pipeline.py ingest data into the pipeline.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the orchestrator.
- Capability inventory: The skill possesses file system write access and the ability to execute subprocesses across the pipeline.
- Sanitization: The script uses argparse to enforce types and choices for some parameters, and resolves file paths using os.path.abspath to maintain consistency.
Audit Metadata