The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface.
Ingestion points: The skill ingests potentially untrusted data from the brand kit and existing templates via the orshot_get_brand_kit and orshot_get_studio_template tools as specified in the SKILL.md workflow.
Boundary markers: There are no explicit markers or instructions defined to isolate or disregard instructions that might be embedded within the retrieved brand colors, fonts, or template content.
Capability inventory: The skill has the capability to perform creation and modification tasks using orshot_create_template_design and orshot_patch_template_elements, which could be influenced by the ingested data.
Sanitization: No sanitization or validation mechanisms are implemented for the content fetched from the MCP tools before it is used in design generation.

orshot-design