rewriting-methodology
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external screenplay data provided by the user to perform analysis, grading, and rewriting. This creates a surface for indirect prompt injection where malicious instructions could be embedded within the script content to override the agent's behavior.
- Ingestion points: The screenplay text being analyzed throughout the 6-step process.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potential commands within the screenplay text.
- Capability inventory: The skill enables the agent to evaluate, grade, and modify text based on specific criteria (e.g., scene compression, dialogue trimming).
- Sanitization: There is no evidence of input sanitization or filtering for the screenplay content.
Audit Metadata