NYC

video-outline-generation

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (INFO): The skill processes external, untrusted data (video briefs), which constitutes a potential injection surface.
  • Ingestion points: User-provided video briefs and requests as specified in the description and '何时使用' sections.
  • Boundary markers: Absent; the prompt does not define specific delimiters to isolate user-provided content from instructions.
  • Capability inventory: None; the skill lacks any tools, file system access, or network capabilities. It is restricted to text output.
  • Sanitization: Absent; no explicit filtering or sanitization logic is provided.
  • [No Code] (SAFE): Analysis of the skill file reveals only markdown documentation and natural language templates. No scripts, binaries, or package dependencies were found.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 03:20 AM