beat-sheet

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data (story documents, briefs, bibles) to generate a beat sheet.
  • Ingestion points: Workflow step 1 reads 'core contract, story craft, brief, story bible, characters, and world' from the local file system.
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions are present in the provided instructions.
  • Capability inventory: The skill is instructed to save content to '01_story/beat_sheet.md'. No network operations or code execution capabilities were identified.
  • Sanitization: There are no instructions for sanitizing, validating, or filtering the content ingested from the external documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:40 AM