annotate
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external image files and a
yolo-project.yamlconfiguration file, which provides a surface for indirect prompt injection where malicious instructions could be embedded within the visual or text data. - Ingestion points: Input images,
yolo-project.yamlfile, and YOLO inference results. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between data and instructions during processing.
- Capability inventory: The skill executes a local Python script and has the capability to write corrected YOLO label files to the local file system.
- Sanitization: No sanitization or validation steps for the input data are mentioned in the skill definition.
- [COMMAND_EXECUTION]: The skill's workflow involves executing a local script
python scripts/draw_annotations.pyto prepare images for review. While this is an intended part of the skill's functionality, it represents a command execution capability that handles potentially untrusted image inputs.
Audit Metadata