rip-video

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill reads file paths and task metadata from 'todolist.md', which could be manipulated by an external source.
  • Ingestion points: Processes 'todolist.md' for video IDs and file paths.
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded malicious text within the ingested data.
  • Capability inventory: Calls the 'rip_video' MCP service and updates local files.
  • Sanitization: No validation or escaping of the parsed strings is performed before they are used in tool calls or file system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM