novel-to-video
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted text data from external files.
- Ingestion points: The workflow explicitly instructs the agent to read novel content and extraction elements from user-provided text files (SKILL.md, Step 4).
- Boundary markers: There are no instructions to use delimiters or ignore potential commands embedded within the text files.
- Capability inventory: The agent is directed to create project directories and write multiple prompt and storyboard files based on the ingested content (SKILL.md).
- Sanitization: The workflow does not include any steps for sanitizing or validating the literary content before it is used to drive the generation process.
Audit Metadata