alterlab-vcd-layout-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources (web search results) and local project files (content drafts, brand guidelines, etc.) to inform its design process and file-writing tasks. This represents an attack surface where instructions hidden in those documents could influence the agent's actions.
- Ingestion points: The 'Format & Content Analysis' step explicitly instructs the agent to search the web for references and read existing project files in the environment.
- Boundary markers: The skill does not provide specific instructions or delimiters to the agent to distinguish between data to be processed and instructions to be followed within the ingested files.
- Capability inventory: The skill possesses network search capabilities and file system access (read/write/re-read) to create and iterate on design deliverables.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from web searches or local files before it is used to generate the layout specifications.
Audit Metadata