video-edit

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including ffmpeg, ffprobe, printf, and rm for video processing, file system output, and cleanup operations.
  • [PRIVILEGE_ESCALATION]: Setup instructions for Linux environments specify the use of sudo for package installation via apt, which grants administrative privileges to the installation process.
  • [INDIRECT_PROMPT_INJECTION]: The agent is directed to ingest and process metadata from external video files, creating a vulnerability surface for adversarial instructions embedded in file tags.
  • Ingestion points: Technical metadata and stream information extracted by ffprobe in JSON format from user-supplied video files.
  • Boundary markers: Not present; the instructions provide no delimiters or warnings to the agent to treat metadata as untrusted or to ignore embedded natural language.
  • Capability inventory: The skill enables execution of ffmpeg with file overwrite permissions (-y) and file deletion via rm.
  • Sanitization: Metadata values are not filtered, validated, or sanitized before being returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM