alterlab-vcd-layout-designer
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing external, untrusted data to generate design deliverables.\n
- Ingestion points: The agent is instructed in the 'Workflow' section to read content drafts, image assets, and brand guidelines from project files, and to perform web searches for editorial references.\n
- Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard instructions found within the processed files or web content.\n
- Capability inventory: The skill has the capability to read local files, conduct web searches, and write multiple markdown files (e.g., '{project}-grid-spec.md') directly to the project directory.\n
- Sanitization: The skill instructions do not include requirements for sanitizing or escaping content retrieved from external sources before it is processed or used in generated files.
Audit Metadata