od-video-frame-data-chart-nyt
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to construct a brief for design tools without using boundary markers or sanitization. - Ingestion points:
$ARGUMENTSinSKILL.md. - Boundary markers: None present around the interpolated variable.
- Capability inventory: Uses MCP tools (
prepare_open_design_brief,list_open_design_design_systems,recommend_open_design_design_systems,register_open_design_artifact) and general file-editing tools. - Sanitization: No sanitization or validation of the input is performed before processing.
Audit Metadata