novel-to-script
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by processing external novel text.
- Ingestion points: Novel content is provided by the user and processed by the agent (SKILL.md, Step 1).
- Boundary markers: The instructions do not define delimiters or provide specific warnings to ignore instructions embedded within the processed novel data.
- Capability inventory: The skill uses the Write tool to save files to the local file system (SKILL.md, Step 5).
- Sanitization: The skill lacks input validation or explicit instructions for the agent to filter out or ignore commands contained within the novel text.
Audit Metadata