verify

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the ffprobe command-line utility to extract metadata from video files. This is a standard and expected operation for the technical verification of media assets.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it ingests and processes external data (video files and tool outputs).
  • Ingestion points: Video deliverables and the JSON output from the ffprobe command in SKILL.md.
  • Boundary markers: No specific delimiters are defined for the ingested metadata or tool output.
  • Capability inventory: Executes ffprobe via subprocess and performs text-based verification of output.
  • Sanitization: No explicit sanitization or validation of the filename or metadata content is described within the instructions.
  • Context: This behavior is intrinsic to the skill's primary function of deliverable verification and is evaluated as safe within this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:32 AM