storyboard-grid-to-video

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill's instructions and reference files do not contain any malicious code, obfuscation, or unauthorized access patterns. The functionality is consistent with its stated purpose of assisting in video storyboarding.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external data from references/cases.md and user-provided inputs to generate video prompts.
  • Ingestion points: Case summaries, prompt excerpts, and URLs in references/cases.md, plus user-supplied character and action requirements.
  • Boundary markers: The skill uses a 'reference contract' (Preserve/Replace/Avoid) to explicitly delineate which structural traits are derived from evidence versus which are supplied by the user.
  • Capability inventory: Prompt generation and inspection of media via agent-controlled tools (browser/image viewer).
  • Sanitization: None, but the logical workflow enforces a separation of concerns that mitigates accidental instruction execution.
  • [EXTERNAL_DOWNLOADS]: The skill references external video and image assets hosted on goodcase.ai and x.com. These references are used for visual grounding and media inspection as part of the storyboarding process and do not involve the execution of remote code or dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 03:41 AM