image-resize

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the agent-media CLI to perform image transformations. This behavior is consistent with the skill's stated purpose of resizing media files.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external input through the --in parameter which can be a file path or a URL.
  • Ingestion points: File paths or URLs provided via the --in argument in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are defined for the input path.
  • Capability inventory: The skill triggers subprocess execution of the vendor-provided agent-media tool.
  • Sanitization: Input validation and sanitization are handled by the underlying agent-media CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 07:52 AM