positioning
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references Google Fonts (fonts.googleapis.com and fonts.gstatic.com) to style the generated HTML positioning documents.
- [COMMAND_EXECUTION]: The skill utilizes vendor-specific tools including get_entity, find_motion_icp, and update_motion_playbook to retrieve and update marketing context and project data.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by loading information from shared project context and evidence files into messaging templates. (1) Ingestion points: references/task-method.md specifies loading gtm-context.md and evidence-and-inputs.md. (2) Boundary markers: No specific delimiters or safety instructions are defined for the interpolated content. (3) Capability inventory: The skill can read and write to the workspace via vendor tools and generate visual HTML artifacts. (4) Sanitization: No explicit validation or filtering steps are documented for the ingested inputs.
Audit Metadata