creator-screenwriter

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files (character briefs and director notes), which is an inherent part of its collaborative workflow but represents a surface for indirect prompt injection.
  • Ingestion points: Files located in project/characters/ and project/continuity/ (specifically creator-director-vision.md and revision-notes-to-creator-screenwriter.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the input data.
  • Capability inventory: The skill has the capability to write to the file system at project/screenplay/* and project/bible/evidence-table.md.
  • Sanitization: Content from ingested files is not sanitized or escaped before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 07:50 AM